Hugging Face's logo

shi3z
/
mlx-karakuri-lm-8x7b-instruct-v0.1

Text Generation
Transformers
Safetensors
MLX
English
Japanese
mixtral
steerlm
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1

Upload folder using huggingface_hub

#1
by shi3z - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+94709
-0
Files changed (14) hide show
  1. README.md +40 -0
  2. added_tokens.json +130 -0
  3. config.json +34 -0
  4. model-00001-of-00006.safetensors +3 -0
  5. model-00002-of-00006.safetensors +3 -0
  6. model-00003-of-00006.safetensors +3 -0
  7. model-00004-of-00006.safetensors +3 -0
  8. model-00005-of-00006.safetensors +3 -0
  9. model-00006-of-00006.safetensors +3 -0
  10. model.safetensors.index.json +846 -0
  11. special_tokens_map.json +153 -0
  12. tokenizer.json +0 -0
  13. tokenizer.model +3 -0
  14. tokenizer_config.json +1210 -0
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
3
+ datasets:
4
+ - databricks/databricks-dolly-15k
5
+ - glaiveai/glaive-code-assistant-v3
6
+ - glaiveai/glaive-function-calling-v2
7
+ - gretelai/synthetic_text_to_sql
8
+ - meta-math/MetaMathQA
9
+ - microsoft/orca-math-word-problems-200k
10
+ - neural-bridge/rag-dataset-12000
11
+ - neural-bridge/rag-hallucination-dataset-1000
12
+ - nvidia/HelpSteer
13
+ - OpenAssistant/oasst2
14
+ language:
15
+ - en
16
+ - ja
17
+ library_name: transformers
18
+ license: apache-2.0
19
+ tags:
20
+ - mixtral
21
+ - steerlm
22
+ - mlx
23
+ ---
24
+
25
+ # shi3z/mlx-karakuri-lm-8x7b-instruct-v0.1
26
+
27
+ The Model [shi3z/mlx-karakuri-lm-8x7b-instruct-v0.1](https://huggingface.co/shi3z/mlx-karakuri-lm-8x7b-instruct-v0.1) was converted to MLX format from [karakuri-ai/karakuri-lm-8x7b-instruct-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-instruct-v0.1) using mlx-lm version **0.17.0**.
28
+
29
+ ## Use with mlx
30
+
31
+ ```bash
32
+ pip install mlx-lm
33
+ ```
34
+
35
+ ```python
36
+ from mlx_lm import load, generate
37
+
38
+ model, tokenizer = load("shi3z/mlx-karakuri-lm-8x7b-instruct-v0.1")
39
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
40
+ ```
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|CHATBOT_TOKEN|>": 32003,
3
+ "<|END_OF_TURN_TOKEN|>": 32001,
4
+ "<|EXTRA_100_TOKEN|>": 32100,
5
+ "<|EXTRA_101_TOKEN|>": 32101,
6
+ "<|EXTRA_102_TOKEN|>": 32102,
7
+ "<|EXTRA_103_TOKEN|>": 32103,
8
+ "<|EXTRA_104_TOKEN|>": 32104,
9
+ "<|EXTRA_105_TOKEN|>": 32105,
10
+ "<|EXTRA_106_TOKEN|>": 32106,
11
+ "<|EXTRA_107_TOKEN|>": 32107,
12
+ "<|EXTRA_108_TOKEN|>": 32108,
13
+ "<|EXTRA_109_TOKEN|>": 32109,
14
+ "<|EXTRA_10_TOKEN|>": 32010,
15
+ "<|EXTRA_110_TOKEN|>": 32110,
16
+ "<|EXTRA_111_TOKEN|>": 32111,
17
+ "<|EXTRA_112_TOKEN|>": 32112,
18
+ "<|EXTRA_113_TOKEN|>": 32113,
19
+ "<|EXTRA_114_TOKEN|>": 32114,
20
+ "<|EXTRA_115_TOKEN|>": 32115,
21
+ "<|EXTRA_116_TOKEN|>": 32116,
22
+ "<|EXTRA_117_TOKEN|>": 32117,
23
+ "<|EXTRA_118_TOKEN|>": 32118,
24
+ "<|EXTRA_119_TOKEN|>": 32119,
25
+ "<|EXTRA_11_TOKEN|>": 32011,
26
+ "<|EXTRA_120_TOKEN|>": 32120,
27
+ "<|EXTRA_121_TOKEN|>": 32121,
28
+ "<|EXTRA_122_TOKEN|>": 32122,
29
+ "<|EXTRA_123_TOKEN|>": 32123,
30
+ "<|EXTRA_124_TOKEN|>": 32124,
31
+ "<|EXTRA_125_TOKEN|>": 32125,
32
+ "<|EXTRA_126_TOKEN|>": 32126,
33
+ "<|EXTRA_127_TOKEN|>": 32127,
34
+ "<|EXTRA_12_TOKEN|>": 32012,
35
+ "<|EXTRA_13_TOKEN|>": 32013,
36
+ "<|EXTRA_14_TOKEN|>": 32014,
37
+ "<|EXTRA_15_TOKEN|>": 32015,
38
+ "<|EXTRA_16_TOKEN|>": 32016,
39
+ "<|EXTRA_17_TOKEN|>": 32017,
40
+ "<|EXTRA_18_TOKEN|>": 32018,
41
+ "<|EXTRA_19_TOKEN|>": 32019,
42
+ "<|EXTRA_20_TOKEN|>": 32020,
43
+ "<|EXTRA_21_TOKEN|>": 32021,
44
+ "<|EXTRA_22_TOKEN|>": 32022,
45
+ "<|EXTRA_23_TOKEN|>": 32023,
46
+ "<|EXTRA_24_TOKEN|>": 32024,
47
+ "<|EXTRA_25_TOKEN|>": 32025,
48
+ "<|EXTRA_26_TOKEN|>": 32026,
49
+ "<|EXTRA_27_TOKEN|>": 32027,
50
+ "<|EXTRA_28_TOKEN|>": 32028,
51
+ "<|EXTRA_29_TOKEN|>": 32029,
52
+ "<|EXTRA_30_TOKEN|>": 32030,
53
+ "<|EXTRA_31_TOKEN|>": 32031,
54
+ "<|EXTRA_32_TOKEN|>": 32032,
55
+ "<|EXTRA_33_TOKEN|>": 32033,
56
+ "<|EXTRA_34_TOKEN|>": 32034,
57
+ "<|EXTRA_35_TOKEN|>": 32035,
58
+ "<|EXTRA_36_TOKEN|>": 32036,
59
+ "<|EXTRA_37_TOKEN|>": 32037,
60
+ "<|EXTRA_38_TOKEN|>": 32038,
61
+ "<|EXTRA_39_TOKEN|>": 32039,
62
+ "<|EXTRA_40_TOKEN|>": 32040,
63
+ "<|EXTRA_41_TOKEN|>": 32041,
64
+ "<|EXTRA_42_TOKEN|>": 32042,
65
+ "<|EXTRA_43_TOKEN|>": 32043,
66
+ "<|EXTRA_44_TOKEN|>": 32044,
67
+ "<|EXTRA_45_TOKEN|>": 32045,
68
+ "<|EXTRA_46_TOKEN|>": 32046,
69
+ "<|EXTRA_47_TOKEN|>": 32047,
70
+ "<|EXTRA_48_TOKEN|>": 32048,
71
+ "<|EXTRA_49_TOKEN|>": 32049,
72
+ "<|EXTRA_50_TOKEN|>": 32050,
73
+ "<|EXTRA_51_TOKEN|>": 32051,
74
+ "<|EXTRA_52_TOKEN|>": 32052,
75
+ "<|EXTRA_53_TOKEN|>": 32053,
76
+ "<|EXTRA_54_TOKEN|>": 32054,
77
+ "<|EXTRA_55_TOKEN|>": 32055,
78
+ "<|EXTRA_56_TOKEN|>": 32056,
79
+ "<|EXTRA_57_TOKEN|>": 32057,
80
+ "<|EXTRA_58_TOKEN|>": 32058,
81
+ "<|EXTRA_59_TOKEN|>": 32059,
82
+ "<|EXTRA_5_TOKEN|>": 32005,
83
+ "<|EXTRA_60_TOKEN|>": 32060,
84
+ "<|EXTRA_61_TOKEN|>": 32061,
85
+ "<|EXTRA_62_TOKEN|>": 32062,
86
+ "<|EXTRA_63_TOKEN|>": 32063,
87
+ "<|EXTRA_64_TOKEN|>": 32064,
88
+ "<|EXTRA_65_TOKEN|>": 32065,
89
+ "<|EXTRA_66_TOKEN|>": 32066,
90
+ "<|EXTRA_67_TOKEN|>": 32067,
91
+ "<|EXTRA_68_TOKEN|>": 32068,
92
+ "<|EXTRA_69_TOKEN|>": 32069,
93
+ "<|EXTRA_6_TOKEN|>": 32006,
94
+ "<|EXTRA_70_TOKEN|>": 32070,
95
+ "<|EXTRA_71_TOKEN|>": 32071,
96
+ "<|EXTRA_72_TOKEN|>": 32072,
97
+ "<|EXTRA_73_TOKEN|>": 32073,
98
+ "<|EXTRA_74_TOKEN|>": 32074,
99
+ "<|EXTRA_75_TOKEN|>": 32075,
100
+ "<|EXTRA_76_TOKEN|>": 32076,
101
+ "<|EXTRA_77_TOKEN|>": 32077,
102
+ "<|EXTRA_78_TOKEN|>": 32078,
103
+ "<|EXTRA_79_TOKEN|>": 32079,
104
+ "<|EXTRA_7_TOKEN|>": 32007,
105
+ "<|EXTRA_80_TOKEN|>": 32080,
106
+ "<|EXTRA_81_TOKEN|>": 32081,
107
+ "<|EXTRA_82_TOKEN|>": 32082,
108
+ "<|EXTRA_83_TOKEN|>": 32083,
109
+ "<|EXTRA_84_TOKEN|>": 32084,
110
+ "<|EXTRA_85_TOKEN|>": 32085,
111
+ "<|EXTRA_86_TOKEN|>": 32086,
112
+ "<|EXTRA_87_TOKEN|>": 32087,
113
+ "<|EXTRA_88_TOKEN|>": 32088,
114
+ "<|EXTRA_89_TOKEN|>": 32089,
115
+ "<|EXTRA_8_TOKEN|>": 32008,
116
+ "<|EXTRA_90_TOKEN|>": 32090,
117
+ "<|EXTRA_91_TOKEN|>": 32091,
118
+ "<|EXTRA_92_TOKEN|>": 32092,
119
+ "<|EXTRA_93_TOKEN|>": 32093,
120
+ "<|EXTRA_94_TOKEN|>": 32094,
121
+ "<|EXTRA_95_TOKEN|>": 32095,
122
+ "<|EXTRA_96_TOKEN|>": 32096,
123
+ "<|EXTRA_97_TOKEN|>": 32097,
124
+ "<|EXTRA_98_TOKEN|>": 32098,
125
+ "<|EXTRA_99_TOKEN|>": 32099,
126
+ "<|EXTRA_9_TOKEN|>": 32009,
127
+ "<|START_OF_TURN_TOKEN|>": 32000,
128
+ "<|SYSTEM_TOKEN|>": 32004,
129
+ "<|USER_TOKEN|>": 32002
130
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MixtralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32001,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mixtral",
14
+ "num_attention_heads": 32,
15
+ "num_experts_per_tok": 2,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "num_local_experts": 8,
19
+ "output_router_logits": false,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 4
23
+ },
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_theta": 1000000.0,
26
+ "router_aux_loss_coef": 0.02,
27
+ "router_jitter_noise": 0.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.41.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32128
34
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48250b5808a16bb122912569f1718821a1f0465ed0352c53d49ffde7a3a56dcd
3
+ size 5260004373
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e376ce051e17dc35363d72fad5e4cbb2f6de2aa4b85c94baebadf62bc0c6dd03
3
+ size 5162368126
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f004956f0d741a811231b36e2f26904a066e7ce53b42cd90420dce60873b32c6
3
+ size 5185997917
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da62dbb7f5b9aef894aa1a3ead0a3bbb4fe2eb4c1f4571c6ff35f67f11ce92fb
3
+ size 5162368162
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d101e21968803ab025469724106dc36532bf6bdad4d7be86d2970701e9335afc
3
+ size 5162368202
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0551e56d6ca147bd810dcd68cb726203e41cdd269dddaef200d2101c845ea793
3
+ size 338289648
model.safetensors.index.json ADDED
@@ -0,0 +1,846 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26271293440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model-00006-of-00006.safetensors",
7
+ "lm_head.scales": "model-00006-of-00006.safetensors",
8
+ "lm_head.weight": "model-00006-of-00006.safetensors",
9
+ "model.embed_tokens.biases": "model-00001-of-00006.safetensors",
10
+ "model.embed_tokens.scales": "model-00001-of-00006.safetensors",
11
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
20
+ "model.layers.0.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.0.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
22
+ "model.layers.0.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
23
+ "model.layers.0.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
27
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
28
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
30
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
31
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
33
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
34
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
35
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
36
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
37
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
38
+ "model.layers.1.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
39
+ "model.layers.1.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
40
+ "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
41
+ "model.layers.1.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
42
+ "model.layers.1.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
43
+ "model.layers.1.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
44
+ "model.layers.1.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
45
+ "model.layers.1.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
46
+ "model.layers.1.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
47
+ "model.layers.1.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
48
+ "model.layers.1.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
49
+ "model.layers.1.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
50
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
51
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
52
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
53
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
54
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
55
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
56
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
57
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
58
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
59
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
60
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
61
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
62
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
63
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
64
+ "model.layers.10.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
65
+ "model.layers.10.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
66
+ "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.10.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
68
+ "model.layers.10.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
69
+ "model.layers.10.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.10.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
71
+ "model.layers.10.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
72
+ "model.layers.10.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.10.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
74
+ "model.layers.10.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
75
+ "model.layers.10.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
77
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
79
+ "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
80
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.10.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
82
+ "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
83
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
85
+ "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
86
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
88
+ "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
89
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.11.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
91
+ "model.layers.11.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
92
+ "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
93
+ "model.layers.11.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
94
+ "model.layers.11.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
95
+ "model.layers.11.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
96
+ "model.layers.11.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
97
+ "model.layers.11.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
98
+ "model.layers.11.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.11.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
100
+ "model.layers.11.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
101
+ "model.layers.11.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
102
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
103
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
104
+ "model.layers.11.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
105
+ "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
106
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
107
+ "model.layers.11.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
108
+ "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
109
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
110
+ "model.layers.11.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
111
+ "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
112
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
113
+ "model.layers.11.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
114
+ "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
115
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
116
+ "model.layers.12.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
117
+ "model.layers.12.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
118
+ "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
119
+ "model.layers.12.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
120
+ "model.layers.12.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
121
+ "model.layers.12.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.12.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
123
+ "model.layers.12.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
124
+ "model.layers.12.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
125
+ "model.layers.12.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
126
+ "model.layers.12.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
127
+ "model.layers.12.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
128
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.12.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
131
+ "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
132
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
133
+ "model.layers.12.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
134
+ "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
135
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
136
+ "model.layers.12.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
137
+ "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
138
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
139
+ "model.layers.12.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
140
+ "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
141
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
142
+ "model.layers.13.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
143
+ "model.layers.13.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
144
+ "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.13.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
146
+ "model.layers.13.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
147
+ "model.layers.13.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.13.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
149
+ "model.layers.13.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
150
+ "model.layers.13.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.13.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
152
+ "model.layers.13.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
153
+ "model.layers.13.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
154
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
155
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
156
+ "model.layers.13.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
157
+ "model.layers.13.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
158
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.13.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
160
+ "model.layers.13.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
161
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
162
+ "model.layers.13.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
163
+ "model.layers.13.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
164
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.13.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
166
+ "model.layers.13.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
167
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.14.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
169
+ "model.layers.14.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
170
+ "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
171
+ "model.layers.14.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
172
+ "model.layers.14.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
173
+ "model.layers.14.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.14.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
175
+ "model.layers.14.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
176
+ "model.layers.14.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.14.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
178
+ "model.layers.14.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
179
+ "model.layers.14.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
180
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
182
+ "model.layers.14.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
183
+ "model.layers.14.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
184
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
185
+ "model.layers.14.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
186
+ "model.layers.14.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
187
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
188
+ "model.layers.14.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
189
+ "model.layers.14.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
190
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
191
+ "model.layers.14.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
192
+ "model.layers.14.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
193
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
194
+ "model.layers.15.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
195
+ "model.layers.15.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
196
+ "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
197
+ "model.layers.15.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
198
+ "model.layers.15.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
199
+ "model.layers.15.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
200
+ "model.layers.15.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
201
+ "model.layers.15.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
202
+ "model.layers.15.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
203
+ "model.layers.15.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
204
+ "model.layers.15.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
205
+ "model.layers.15.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
206
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
207
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
208
+ "model.layers.15.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
209
+ "model.layers.15.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
210
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
211
+ "model.layers.15.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
212
+ "model.layers.15.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
213
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
214
+ "model.layers.15.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
215
+ "model.layers.15.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
216
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
217
+ "model.layers.15.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
218
+ "model.layers.15.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
219
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.16.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
221
+ "model.layers.16.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
222
+ "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
223
+ "model.layers.16.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
224
+ "model.layers.16.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
225
+ "model.layers.16.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
226
+ "model.layers.16.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
227
+ "model.layers.16.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
228
+ "model.layers.16.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
229
+ "model.layers.16.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
230
+ "model.layers.16.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
231
+ "model.layers.16.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
232
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
233
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
234
+ "model.layers.16.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
235
+ "model.layers.16.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
236
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
237
+ "model.layers.16.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
238
+ "model.layers.16.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
239
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
240
+ "model.layers.16.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
241
+ "model.layers.16.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
242
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
243
+ "model.layers.16.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
244
+ "model.layers.16.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
245
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
246
+ "model.layers.17.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
247
+ "model.layers.17.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
248
+ "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
249
+ "model.layers.17.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
250
+ "model.layers.17.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
251
+ "model.layers.17.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
252
+ "model.layers.17.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
253
+ "model.layers.17.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
254
+ "model.layers.17.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
255
+ "model.layers.17.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
256
+ "model.layers.17.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
257
+ "model.layers.17.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
258
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
259
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
260
+ "model.layers.17.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
261
+ "model.layers.17.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
262
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
263
+ "model.layers.17.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
264
+ "model.layers.17.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
265
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
266
+ "model.layers.17.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
267
+ "model.layers.17.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
268
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
269
+ "model.layers.17.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
270
+ "model.layers.17.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
271
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
272
+ "model.layers.18.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
273
+ "model.layers.18.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
274
+ "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
275
+ "model.layers.18.block_sparse_moe.switch_mlp.down_proj.biases": "model-00003-of-00006.safetensors",
276
+ "model.layers.18.block_sparse_moe.switch_mlp.down_proj.scales": "model-00003-of-00006.safetensors",
277
+ "model.layers.18.block_sparse_moe.switch_mlp.down_proj.weight": "model-00003-of-00006.safetensors",
278
+ "model.layers.18.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00003-of-00006.safetensors",
279
+ "model.layers.18.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00003-of-00006.safetensors",
280
+ "model.layers.18.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
281
+ "model.layers.18.block_sparse_moe.switch_mlp.up_proj.biases": "model-00003-of-00006.safetensors",
282
+ "model.layers.18.block_sparse_moe.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
283
+ "model.layers.18.block_sparse_moe.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
284
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
285
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
286
+ "model.layers.18.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
287
+ "model.layers.18.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
288
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
289
+ "model.layers.18.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
290
+ "model.layers.18.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
291
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
292
+ "model.layers.18.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
293
+ "model.layers.18.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
294
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
295
+ "model.layers.18.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
296
+ "model.layers.18.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
297
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
298
+ "model.layers.19.block_sparse_moe.gate.biases": "model-00003-of-00006.safetensors",
299
+ "model.layers.19.block_sparse_moe.gate.scales": "model-00003-of-00006.safetensors",
300
+ "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
301
+ "model.layers.19.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
302
+ "model.layers.19.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
303
+ "model.layers.19.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
304
+ "model.layers.19.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
305
+ "model.layers.19.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
306
+ "model.layers.19.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
307
+ "model.layers.19.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
308
+ "model.layers.19.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
309
+ "model.layers.19.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
310
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
311
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
312
+ "model.layers.19.self_attn.k_proj.biases": "model-00003-of-00006.safetensors",
313
+ "model.layers.19.self_attn.k_proj.scales": "model-00003-of-00006.safetensors",
314
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
315
+ "model.layers.19.self_attn.o_proj.biases": "model-00003-of-00006.safetensors",
316
+ "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00006.safetensors",
317
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
318
+ "model.layers.19.self_attn.q_proj.biases": "model-00003-of-00006.safetensors",
319
+ "model.layers.19.self_attn.q_proj.scales": "model-00003-of-00006.safetensors",
320
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
321
+ "model.layers.19.self_attn.v_proj.biases": "model-00003-of-00006.safetensors",
322
+ "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00006.safetensors",
323
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
324
+ "model.layers.2.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
325
+ "model.layers.2.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
326
+ "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
327
+ "model.layers.2.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
328
+ "model.layers.2.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
329
+ "model.layers.2.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
330
+ "model.layers.2.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
331
+ "model.layers.2.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
332
+ "model.layers.2.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
333
+ "model.layers.2.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
334
+ "model.layers.2.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
335
+ "model.layers.2.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
336
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
337
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
338
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
339
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
340
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
341
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
342
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
343
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
344
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
345
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
346
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
347
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
348
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
349
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
350
+ "model.layers.20.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
351
+ "model.layers.20.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
352
+ "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
353
+ "model.layers.20.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
354
+ "model.layers.20.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
355
+ "model.layers.20.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
356
+ "model.layers.20.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
357
+ "model.layers.20.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
358
+ "model.layers.20.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
359
+ "model.layers.20.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
360
+ "model.layers.20.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
361
+ "model.layers.20.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
362
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
363
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
364
+ "model.layers.20.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
365
+ "model.layers.20.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
366
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
367
+ "model.layers.20.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
368
+ "model.layers.20.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
369
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
370
+ "model.layers.20.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
371
+ "model.layers.20.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
372
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
373
+ "model.layers.20.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
374
+ "model.layers.20.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
375
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
376
+ "model.layers.21.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
377
+ "model.layers.21.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
378
+ "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
379
+ "model.layers.21.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
380
+ "model.layers.21.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
381
+ "model.layers.21.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
382
+ "model.layers.21.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
383
+ "model.layers.21.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
384
+ "model.layers.21.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
385
+ "model.layers.21.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
386
+ "model.layers.21.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
387
+ "model.layers.21.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
388
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
389
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
390
+ "model.layers.21.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
391
+ "model.layers.21.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
392
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
393
+ "model.layers.21.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
394
+ "model.layers.21.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
395
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
396
+ "model.layers.21.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
397
+ "model.layers.21.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
398
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
399
+ "model.layers.21.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
400
+ "model.layers.21.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
401
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
402
+ "model.layers.22.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
403
+ "model.layers.22.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
404
+ "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
405
+ "model.layers.22.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
406
+ "model.layers.22.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
407
+ "model.layers.22.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
408
+ "model.layers.22.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
409
+ "model.layers.22.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
410
+ "model.layers.22.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
411
+ "model.layers.22.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
412
+ "model.layers.22.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
413
+ "model.layers.22.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
414
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
415
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
416
+ "model.layers.22.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
417
+ "model.layers.22.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
418
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
419
+ "model.layers.22.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
420
+ "model.layers.22.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
421
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
422
+ "model.layers.22.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
423
+ "model.layers.22.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
424
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
425
+ "model.layers.22.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
426
+ "model.layers.22.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
427
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
428
+ "model.layers.23.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
429
+ "model.layers.23.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
430
+ "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
431
+ "model.layers.23.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
432
+ "model.layers.23.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
433
+ "model.layers.23.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
434
+ "model.layers.23.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
435
+ "model.layers.23.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
436
+ "model.layers.23.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
437
+ "model.layers.23.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
438
+ "model.layers.23.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
439
+ "model.layers.23.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
440
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
441
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
442
+ "model.layers.23.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
443
+ "model.layers.23.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
444
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
445
+ "model.layers.23.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
446
+ "model.layers.23.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
447
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
448
+ "model.layers.23.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
449
+ "model.layers.23.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
450
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
451
+ "model.layers.23.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
452
+ "model.layers.23.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
453
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
454
+ "model.layers.24.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
455
+ "model.layers.24.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
456
+ "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
457
+ "model.layers.24.block_sparse_moe.switch_mlp.down_proj.biases": "model-00004-of-00006.safetensors",
458
+ "model.layers.24.block_sparse_moe.switch_mlp.down_proj.scales": "model-00004-of-00006.safetensors",
459
+ "model.layers.24.block_sparse_moe.switch_mlp.down_proj.weight": "model-00004-of-00006.safetensors",
460
+ "model.layers.24.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
461
+ "model.layers.24.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
462
+ "model.layers.24.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
463
+ "model.layers.24.block_sparse_moe.switch_mlp.up_proj.biases": "model-00004-of-00006.safetensors",
464
+ "model.layers.24.block_sparse_moe.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
465
+ "model.layers.24.block_sparse_moe.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
466
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
467
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
468
+ "model.layers.24.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
469
+ "model.layers.24.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
470
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
471
+ "model.layers.24.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
472
+ "model.layers.24.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
473
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
474
+ "model.layers.24.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
475
+ "model.layers.24.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
476
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
477
+ "model.layers.24.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
478
+ "model.layers.24.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
479
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
480
+ "model.layers.25.block_sparse_moe.gate.biases": "model-00004-of-00006.safetensors",
481
+ "model.layers.25.block_sparse_moe.gate.scales": "model-00004-of-00006.safetensors",
482
+ "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
483
+ "model.layers.25.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
484
+ "model.layers.25.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
485
+ "model.layers.25.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
486
+ "model.layers.25.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00004-of-00006.safetensors",
487
+ "model.layers.25.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00004-of-00006.safetensors",
488
+ "model.layers.25.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
489
+ "model.layers.25.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
490
+ "model.layers.25.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
491
+ "model.layers.25.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
492
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
493
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
494
+ "model.layers.25.self_attn.k_proj.biases": "model-00004-of-00006.safetensors",
495
+ "model.layers.25.self_attn.k_proj.scales": "model-00004-of-00006.safetensors",
496
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
497
+ "model.layers.25.self_attn.o_proj.biases": "model-00004-of-00006.safetensors",
498
+ "model.layers.25.self_attn.o_proj.scales": "model-00004-of-00006.safetensors",
499
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
500
+ "model.layers.25.self_attn.q_proj.biases": "model-00004-of-00006.safetensors",
501
+ "model.layers.25.self_attn.q_proj.scales": "model-00004-of-00006.safetensors",
502
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
503
+ "model.layers.25.self_attn.v_proj.biases": "model-00004-of-00006.safetensors",
504
+ "model.layers.25.self_attn.v_proj.scales": "model-00004-of-00006.safetensors",
505
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
506
+ "model.layers.26.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
507
+ "model.layers.26.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
508
+ "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
509
+ "model.layers.26.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
510
+ "model.layers.26.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
511
+ "model.layers.26.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
512
+ "model.layers.26.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
513
+ "model.layers.26.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
514
+ "model.layers.26.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
515
+ "model.layers.26.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
516
+ "model.layers.26.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
517
+ "model.layers.26.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
518
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
519
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
520
+ "model.layers.26.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
521
+ "model.layers.26.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
522
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
523
+ "model.layers.26.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
524
+ "model.layers.26.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
525
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
526
+ "model.layers.26.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
527
+ "model.layers.26.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
528
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
529
+ "model.layers.26.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
530
+ "model.layers.26.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
531
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
532
+ "model.layers.27.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
533
+ "model.layers.27.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
534
+ "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
535
+ "model.layers.27.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
536
+ "model.layers.27.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
537
+ "model.layers.27.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
538
+ "model.layers.27.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
539
+ "model.layers.27.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
540
+ "model.layers.27.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
541
+ "model.layers.27.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
542
+ "model.layers.27.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
543
+ "model.layers.27.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
544
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
545
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
546
+ "model.layers.27.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
547
+ "model.layers.27.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
548
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
549
+ "model.layers.27.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
550
+ "model.layers.27.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
551
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
552
+ "model.layers.27.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
553
+ "model.layers.27.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
554
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
555
+ "model.layers.27.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
556
+ "model.layers.27.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
557
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
558
+ "model.layers.28.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
559
+ "model.layers.28.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
560
+ "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
561
+ "model.layers.28.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
562
+ "model.layers.28.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
563
+ "model.layers.28.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
564
+ "model.layers.28.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
565
+ "model.layers.28.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
566
+ "model.layers.28.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
567
+ "model.layers.28.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
568
+ "model.layers.28.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
569
+ "model.layers.28.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
570
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
571
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
572
+ "model.layers.28.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
573
+ "model.layers.28.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
574
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
575
+ "model.layers.28.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
576
+ "model.layers.28.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
577
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
578
+ "model.layers.28.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
579
+ "model.layers.28.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
580
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
581
+ "model.layers.28.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
582
+ "model.layers.28.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
583
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
584
+ "model.layers.29.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
585
+ "model.layers.29.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
586
+ "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
587
+ "model.layers.29.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
588
+ "model.layers.29.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
589
+ "model.layers.29.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
590
+ "model.layers.29.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
591
+ "model.layers.29.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
592
+ "model.layers.29.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
593
+ "model.layers.29.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
594
+ "model.layers.29.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
595
+ "model.layers.29.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
596
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
597
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
598
+ "model.layers.29.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
599
+ "model.layers.29.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
600
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
601
+ "model.layers.29.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
602
+ "model.layers.29.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
603
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
604
+ "model.layers.29.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
605
+ "model.layers.29.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
606
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
607
+ "model.layers.29.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
608
+ "model.layers.29.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
609
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
610
+ "model.layers.3.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
611
+ "model.layers.3.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
612
+ "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
613
+ "model.layers.3.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
614
+ "model.layers.3.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
615
+ "model.layers.3.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
616
+ "model.layers.3.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
617
+ "model.layers.3.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
618
+ "model.layers.3.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
619
+ "model.layers.3.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
620
+ "model.layers.3.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
621
+ "model.layers.3.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
622
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
623
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
624
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
625
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
626
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
627
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
628
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
629
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
630
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
631
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
632
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
633
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
634
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
635
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
636
+ "model.layers.30.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
637
+ "model.layers.30.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
638
+ "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
639
+ "model.layers.30.block_sparse_moe.switch_mlp.down_proj.biases": "model-00005-of-00006.safetensors",
640
+ "model.layers.30.block_sparse_moe.switch_mlp.down_proj.scales": "model-00005-of-00006.safetensors",
641
+ "model.layers.30.block_sparse_moe.switch_mlp.down_proj.weight": "model-00005-of-00006.safetensors",
642
+ "model.layers.30.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
643
+ "model.layers.30.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
644
+ "model.layers.30.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
645
+ "model.layers.30.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
646
+ "model.layers.30.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
647
+ "model.layers.30.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
648
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
649
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
650
+ "model.layers.30.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
651
+ "model.layers.30.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
652
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
653
+ "model.layers.30.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
654
+ "model.layers.30.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
655
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
656
+ "model.layers.30.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
657
+ "model.layers.30.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
658
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
659
+ "model.layers.30.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
660
+ "model.layers.30.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
661
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
662
+ "model.layers.31.block_sparse_moe.gate.biases": "model-00005-of-00006.safetensors",
663
+ "model.layers.31.block_sparse_moe.gate.scales": "model-00005-of-00006.safetensors",
664
+ "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
665
+ "model.layers.31.block_sparse_moe.switch_mlp.down_proj.biases": "model-00006-of-00006.safetensors",
666
+ "model.layers.31.block_sparse_moe.switch_mlp.down_proj.scales": "model-00006-of-00006.safetensors",
667
+ "model.layers.31.block_sparse_moe.switch_mlp.down_proj.weight": "model-00006-of-00006.safetensors",
668
+ "model.layers.31.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00005-of-00006.safetensors",
669
+ "model.layers.31.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00005-of-00006.safetensors",
670
+ "model.layers.31.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
671
+ "model.layers.31.block_sparse_moe.switch_mlp.up_proj.biases": "model-00005-of-00006.safetensors",
672
+ "model.layers.31.block_sparse_moe.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
673
+ "model.layers.31.block_sparse_moe.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
674
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
675
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
676
+ "model.layers.31.self_attn.k_proj.biases": "model-00005-of-00006.safetensors",
677
+ "model.layers.31.self_attn.k_proj.scales": "model-00005-of-00006.safetensors",
678
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
679
+ "model.layers.31.self_attn.o_proj.biases": "model-00005-of-00006.safetensors",
680
+ "model.layers.31.self_attn.o_proj.scales": "model-00005-of-00006.safetensors",
681
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
682
+ "model.layers.31.self_attn.q_proj.biases": "model-00005-of-00006.safetensors",
683
+ "model.layers.31.self_attn.q_proj.scales": "model-00005-of-00006.safetensors",
684
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
685
+ "model.layers.31.self_attn.v_proj.biases": "model-00005-of-00006.safetensors",
686
+ "model.layers.31.self_attn.v_proj.scales": "model-00005-of-00006.safetensors",
687
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
688
+ "model.layers.4.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
689
+ "model.layers.4.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
690
+ "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
691
+ "model.layers.4.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
692
+ "model.layers.4.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
693
+ "model.layers.4.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
694
+ "model.layers.4.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
695
+ "model.layers.4.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
696
+ "model.layers.4.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
697
+ "model.layers.4.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
698
+ "model.layers.4.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
699
+ "model.layers.4.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
700
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
701
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
702
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
703
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
704
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
705
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
706
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
707
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
708
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
709
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
710
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
711
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
712
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
713
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
714
+ "model.layers.5.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
715
+ "model.layers.5.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
716
+ "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
717
+ "model.layers.5.block_sparse_moe.switch_mlp.down_proj.biases": "model-00001-of-00006.safetensors",
718
+ "model.layers.5.block_sparse_moe.switch_mlp.down_proj.scales": "model-00001-of-00006.safetensors",
719
+ "model.layers.5.block_sparse_moe.switch_mlp.down_proj.weight": "model-00001-of-00006.safetensors",
720
+ "model.layers.5.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
721
+ "model.layers.5.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
722
+ "model.layers.5.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
723
+ "model.layers.5.block_sparse_moe.switch_mlp.up_proj.biases": "model-00001-of-00006.safetensors",
724
+ "model.layers.5.block_sparse_moe.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
725
+ "model.layers.5.block_sparse_moe.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
726
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
727
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
728
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
729
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
730
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
731
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
732
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
733
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
734
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
735
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
736
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
737
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
738
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
739
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
740
+ "model.layers.6.block_sparse_moe.gate.biases": "model-00001-of-00006.safetensors",
741
+ "model.layers.6.block_sparse_moe.gate.scales": "model-00001-of-00006.safetensors",
742
+ "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
743
+ "model.layers.6.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
744
+ "model.layers.6.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
745
+ "model.layers.6.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
746
+ "model.layers.6.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00001-of-00006.safetensors",
747
+ "model.layers.6.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00001-of-00006.safetensors",
748
+ "model.layers.6.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
749
+ "model.layers.6.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
750
+ "model.layers.6.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
751
+ "model.layers.6.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
752
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
753
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
754
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00006.safetensors",
755
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00006.safetensors",
756
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
757
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00006.safetensors",
758
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00006.safetensors",
759
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
760
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00006.safetensors",
761
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00006.safetensors",
762
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
763
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00006.safetensors",
764
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00006.safetensors",
765
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
766
+ "model.layers.7.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
767
+ "model.layers.7.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
768
+ "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
769
+ "model.layers.7.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
770
+ "model.layers.7.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
771
+ "model.layers.7.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
772
+ "model.layers.7.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
773
+ "model.layers.7.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
774
+ "model.layers.7.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
775
+ "model.layers.7.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
776
+ "model.layers.7.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
777
+ "model.layers.7.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
778
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
779
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
780
+ "model.layers.7.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
781
+ "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
782
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
783
+ "model.layers.7.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
784
+ "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
785
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
786
+ "model.layers.7.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
787
+ "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
788
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
789
+ "model.layers.7.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
790
+ "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
791
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
792
+ "model.layers.8.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
793
+ "model.layers.8.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
794
+ "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
795
+ "model.layers.8.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
796
+ "model.layers.8.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
797
+ "model.layers.8.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
798
+ "model.layers.8.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
799
+ "model.layers.8.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
800
+ "model.layers.8.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
801
+ "model.layers.8.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
802
+ "model.layers.8.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
803
+ "model.layers.8.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
804
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
805
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
806
+ "model.layers.8.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
807
+ "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
808
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
809
+ "model.layers.8.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
810
+ "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
811
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
812
+ "model.layers.8.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
813
+ "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
814
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
815
+ "model.layers.8.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
816
+ "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
817
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
818
+ "model.layers.9.block_sparse_moe.gate.biases": "model-00002-of-00006.safetensors",
819
+ "model.layers.9.block_sparse_moe.gate.scales": "model-00002-of-00006.safetensors",
820
+ "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
821
+ "model.layers.9.block_sparse_moe.switch_mlp.down_proj.biases": "model-00002-of-00006.safetensors",
822
+ "model.layers.9.block_sparse_moe.switch_mlp.down_proj.scales": "model-00002-of-00006.safetensors",
823
+ "model.layers.9.block_sparse_moe.switch_mlp.down_proj.weight": "model-00002-of-00006.safetensors",
824
+ "model.layers.9.block_sparse_moe.switch_mlp.gate_proj.biases": "model-00002-of-00006.safetensors",
825
+ "model.layers.9.block_sparse_moe.switch_mlp.gate_proj.scales": "model-00002-of-00006.safetensors",
826
+ "model.layers.9.block_sparse_moe.switch_mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
827
+ "model.layers.9.block_sparse_moe.switch_mlp.up_proj.biases": "model-00002-of-00006.safetensors",
828
+ "model.layers.9.block_sparse_moe.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
829
+ "model.layers.9.block_sparse_moe.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
830
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
831
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
832
+ "model.layers.9.self_attn.k_proj.biases": "model-00002-of-00006.safetensors",
833
+ "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00006.safetensors",
834
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
835
+ "model.layers.9.self_attn.o_proj.biases": "model-00002-of-00006.safetensors",
836
+ "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00006.safetensors",
837
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
838
+ "model.layers.9.self_attn.q_proj.biases": "model-00002-of-00006.safetensors",
839
+ "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00006.safetensors",
840
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
841
+ "model.layers.9.self_attn.v_proj.biases": "model-00002-of-00006.safetensors",
842
+ "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00006.safetensors",
843
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
844
+ "model.norm.weight": "model-00006-of-00006.safetensors"
845
+ }
846
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|START_OF_TURN_TOKEN|>",
4
+ "<|END_OF_TURN_TOKEN|>",
5
+ "<|USER_TOKEN|>",
6
+ "<|CHATBOT_TOKEN|>",
7
+ "<|SYSTEM_TOKEN|>",
8
+ "<|EXTRA_5_TOKEN|>",
9
+ "<|EXTRA_6_TOKEN|>",
10
+ "<|EXTRA_7_TOKEN|>",
11
+ "<|EXTRA_8_TOKEN|>",
12
+ "<|EXTRA_9_TOKEN|>",
13
+ "<|EXTRA_10_TOKEN|>",
14
+ "<|EXTRA_11_TOKEN|>",
15
+ "<|EXTRA_12_TOKEN|>",
16
+ "<|EXTRA_13_TOKEN|>",
17
+ "<|EXTRA_14_TOKEN|>",
18
+ "<|EXTRA_15_TOKEN|>",
19
+ "<|EXTRA_16_TOKEN|>",
20
+ "<|EXTRA_17_TOKEN|>",
21
+ "<|EXTRA_18_TOKEN|>",
22
+ "<|EXTRA_19_TOKEN|>",
23
+ "<|EXTRA_20_TOKEN|>",
24
+ "<|EXTRA_21_TOKEN|>",
25
+ "<|EXTRA_22_TOKEN|>",
26
+ "<|EXTRA_23_TOKEN|>",
27
+ "<|EXTRA_24_TOKEN|>",
28
+ "<|EXTRA_25_TOKEN|>",
29
+ "<|EXTRA_26_TOKEN|>",
30
+ "<|EXTRA_27_TOKEN|>",
31
+ "<|EXTRA_28_TOKEN|>",
32
+ "<|EXTRA_29_TOKEN|>",
33
+ "<|EXTRA_30_TOKEN|>",
34
+ "<|EXTRA_31_TOKEN|>",
35
+ "<|EXTRA_32_TOKEN|>",
36
+ "<|EXTRA_33_TOKEN|>",
37
+ "<|EXTRA_34_TOKEN|>",
38
+ "<|EXTRA_35_TOKEN|>",
39
+ "<|EXTRA_36_TOKEN|>",
40
+ "<|EXTRA_37_TOKEN|>",
41
+ "<|EXTRA_38_TOKEN|>",
42
+ "<|EXTRA_39_TOKEN|>",
43
+ "<|EXTRA_40_TOKEN|>",
44
+ "<|EXTRA_41_TOKEN|>",
45
+ "<|EXTRA_42_TOKEN|>",
46
+ "<|EXTRA_43_TOKEN|>",
47
+ "<|EXTRA_44_TOKEN|>",
48
+ "<|EXTRA_45_TOKEN|>",
49
+ "<|EXTRA_46_TOKEN|>",
50
+ "<|EXTRA_47_TOKEN|>",
51
+ "<|EXTRA_48_TOKEN|>",
52
+ "<|EXTRA_49_TOKEN|>",
53
+ "<|EXTRA_50_TOKEN|>",
54
+ "<|EXTRA_51_TOKEN|>",
55
+ "<|EXTRA_52_TOKEN|>",
56
+ "<|EXTRA_53_TOKEN|>",
57
+ "<|EXTRA_54_TOKEN|>",
58
+ "<|EXTRA_55_TOKEN|>",
59
+ "<|EXTRA_56_TOKEN|>",
60
+ "<|EXTRA_57_TOKEN|>",
61
+ "<|EXTRA_58_TOKEN|>",
62
+ "<|EXTRA_59_TOKEN|>",
63
+ "<|EXTRA_60_TOKEN|>",
64
+ "<|EXTRA_61_TOKEN|>",
65
+ "<|EXTRA_62_TOKEN|>",
66
+ "<|EXTRA_63_TOKEN|>",
67
+ "<|EXTRA_64_TOKEN|>",
68
+ "<|EXTRA_65_TOKEN|>",
69
+ "<|EXTRA_66_TOKEN|>",
70
+ "<|EXTRA_67_TOKEN|>",
71
+ "<|EXTRA_68_TOKEN|>",
72
+ "<|EXTRA_69_TOKEN|>",
73
+ "<|EXTRA_70_TOKEN|>",
74
+ "<|EXTRA_71_TOKEN|>",
75
+ "<|EXTRA_72_TOKEN|>",
76
+ "<|EXTRA_73_TOKEN|>",
77
+ "<|EXTRA_74_TOKEN|>",
78
+ "<|EXTRA_75_TOKEN|>",
79
+ "<|EXTRA_76_TOKEN|>",
80
+ "<|EXTRA_77_TOKEN|>",
81
+ "<|EXTRA_78_TOKEN|>",
82
+ "<|EXTRA_79_TOKEN|>",
83
+ "<|EXTRA_80_TOKEN|>",
84
+ "<|EXTRA_81_TOKEN|>",
85
+ "<|EXTRA_82_TOKEN|>",
86
+ "<|EXTRA_83_TOKEN|>",
87
+ "<|EXTRA_84_TOKEN|>",
88
+ "<|EXTRA_85_TOKEN|>",
89
+ "<|EXTRA_86_TOKEN|>",
90
+ "<|EXTRA_87_TOKEN|>",
91
+ "<|EXTRA_88_TOKEN|>",
92
+ "<|EXTRA_89_TOKEN|>",
93
+ "<|EXTRA_90_TOKEN|>",
94
+ "<|EXTRA_91_TOKEN|>",
95
+ "<|EXTRA_92_TOKEN|>",
96
+ "<|EXTRA_93_TOKEN|>",
97
+ "<|EXTRA_94_TOKEN|>",
98
+ "<|EXTRA_95_TOKEN|>",
99
+ "<|EXTRA_96_TOKEN|>",
100
+ "<|EXTRA_97_TOKEN|>",
101
+ "<|EXTRA_98_TOKEN|>",
102
+ "<|EXTRA_99_TOKEN|>",
103
+ "<|EXTRA_100_TOKEN|>",
104
+ "<|EXTRA_101_TOKEN|>",
105
+ "<|EXTRA_102_TOKEN|>",
106
+ "<|EXTRA_103_TOKEN|>",
107
+ "<|EXTRA_104_TOKEN|>",
108
+ "<|EXTRA_105_TOKEN|>",
109
+ "<|EXTRA_106_TOKEN|>",
110
+ "<|EXTRA_107_TOKEN|>",
111
+ "<|EXTRA_108_TOKEN|>",
112
+ "<|EXTRA_109_TOKEN|>",
113
+ "<|EXTRA_110_TOKEN|>",
114
+ "<|EXTRA_111_TOKEN|>",
115
+ "<|EXTRA_112_TOKEN|>",
116
+ "<|EXTRA_113_TOKEN|>",
117
+ "<|EXTRA_114_TOKEN|>",
118
+ "<|EXTRA_115_TOKEN|>",
119
+ "<|EXTRA_116_TOKEN|>",
120
+ "<|EXTRA_117_TOKEN|>",
121
+ "<|EXTRA_118_TOKEN|>",
122
+ "<|EXTRA_119_TOKEN|>",
123
+ "<|EXTRA_120_TOKEN|>",
124
+ "<|EXTRA_121_TOKEN|>",
125
+ "<|EXTRA_122_TOKEN|>",
126
+ "<|EXTRA_123_TOKEN|>",
127
+ "<|EXTRA_124_TOKEN|>",
128
+ "<|EXTRA_125_TOKEN|>",
129
+ "<|EXTRA_126_TOKEN|>",
130
+ "<|EXTRA_127_TOKEN|>"
131
+ ],
132
+ "bos_token": {
133
+ "content": "<s>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ },
139
+ "eos_token": {
140
+ "content": "<|END_OF_TURN_TOKEN|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false
145
+ },
146
+ "unk_token": {
147
+ "content": "<unk>",
148
+ "lstrip": false,
149
+ "normalized": false,
150
+ "rstrip": false,
151
+ "single_word": false
152
+ }
153
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,1210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|START_OF_TURN_TOKEN|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|END_OF_TURN_TOKEN|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|USER_TOKEN|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|CHATBOT_TOKEN|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|SYSTEM_TOKEN|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|EXTRA_5_TOKEN|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|EXTRA_6_TOKEN|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|EXTRA_7_TOKEN|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|EXTRA_8_TOKEN|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|EXTRA_9_TOKEN|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|EXTRA_10_TOKEN|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|EXTRA_11_TOKEN|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|EXTRA_12_TOKEN|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|EXTRA_13_TOKEN|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|EXTRA_14_TOKEN|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|EXTRA_15_TOKEN|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|EXTRA_16_TOKEN|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|EXTRA_17_TOKEN|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|EXTRA_18_TOKEN|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|EXTRA_19_TOKEN|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|EXTRA_20_TOKEN|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|EXTRA_21_TOKEN|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|EXTRA_22_TOKEN|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|EXTRA_23_TOKEN|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|EXTRA_24_TOKEN|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|EXTRA_25_TOKEN|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|EXTRA_26_TOKEN|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|EXTRA_27_TOKEN|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|EXTRA_28_TOKEN|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|EXTRA_29_TOKEN|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|EXTRA_30_TOKEN|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|EXTRA_31_TOKEN|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|EXTRA_32_TOKEN|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|EXTRA_33_TOKEN|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|EXTRA_34_TOKEN|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|EXTRA_35_TOKEN|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|EXTRA_36_TOKEN|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|EXTRA_37_TOKEN|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "32038": {
335
+ "content": "<|EXTRA_38_TOKEN|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "32039": {
343
+ "content": "<|EXTRA_39_TOKEN|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "32040": {
351
+ "content": "<|EXTRA_40_TOKEN|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "32041": {
359
+ "content": "<|EXTRA_41_TOKEN|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "32042": {
367
+ "content": "<|EXTRA_42_TOKEN|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "32043": {
375
+ "content": "<|EXTRA_43_TOKEN|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "32044": {
383
+ "content": "<|EXTRA_44_TOKEN|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "32045": {
391
+ "content": "<|EXTRA_45_TOKEN|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "32046": {
399
+ "content": "<|EXTRA_46_TOKEN|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "32047": {
407
+ "content": "<|EXTRA_47_TOKEN|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "32048": {
415
+ "content": "<|EXTRA_48_TOKEN|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "32049": {
423
+ "content": "<|EXTRA_49_TOKEN|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "32050": {
431
+ "content": "<|EXTRA_50_TOKEN|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "32051": {
439
+ "content": "<|EXTRA_51_TOKEN|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "32052": {
447
+ "content": "<|EXTRA_52_TOKEN|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "32053": {
455
+ "content": "<|EXTRA_53_TOKEN|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "32054": {
463
+ "content": "<|EXTRA_54_TOKEN|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "32055": {
471
+ "content": "<|EXTRA_55_TOKEN|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "32056": {
479
+ "content": "<|EXTRA_56_TOKEN|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "32057": {
487
+ "content": "<|EXTRA_57_TOKEN|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "32058": {
495
+ "content": "<|EXTRA_58_TOKEN|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "32059": {
503
+ "content": "<|EXTRA_59_TOKEN|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "32060": {
511
+ "content": "<|EXTRA_60_TOKEN|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "32061": {
519
+ "content": "<|EXTRA_61_TOKEN|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "32062": {
527
+ "content": "<|EXTRA_62_TOKEN|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "32063": {
535
+ "content": "<|EXTRA_63_TOKEN|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "32064": {
543
+ "content": "<|EXTRA_64_TOKEN|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "32065": {
551
+ "content": "<|EXTRA_65_TOKEN|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "32066": {
559
+ "content": "<|EXTRA_66_TOKEN|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "32067": {
567
+ "content": "<|EXTRA_67_TOKEN|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "32068": {
575
+ "content": "<|EXTRA_68_TOKEN|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "32069": {
583
+ "content": "<|EXTRA_69_TOKEN|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "32070": {
591
+ "content": "<|EXTRA_70_TOKEN|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "32071": {
599
+ "content": "<|EXTRA_71_TOKEN|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "32072": {
607
+ "content": "<|EXTRA_72_TOKEN|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "32073": {
615
+ "content": "<|EXTRA_73_TOKEN|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "32074": {
623
+ "content": "<|EXTRA_74_TOKEN|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "32075": {
631
+ "content": "<|EXTRA_75_TOKEN|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "32076": {
639
+ "content": "<|EXTRA_76_TOKEN|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "32077": {
647
+ "content": "<|EXTRA_77_TOKEN|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "32078": {
655
+ "content": "<|EXTRA_78_TOKEN|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "32079": {
663
+ "content": "<|EXTRA_79_TOKEN|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "32080": {
671
+ "content": "<|EXTRA_80_TOKEN|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "32081": {
679
+ "content": "<|EXTRA_81_TOKEN|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "32082": {
687
+ "content": "<|EXTRA_82_TOKEN|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "32083": {
695
+ "content": "<|EXTRA_83_TOKEN|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "32084": {
703
+ "content": "<|EXTRA_84_TOKEN|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "32085": {
711
+ "content": "<|EXTRA_85_TOKEN|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "32086": {
719
+ "content": "<|EXTRA_86_TOKEN|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "32087": {
727
+ "content": "<|EXTRA_87_TOKEN|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "32088": {
735
+ "content": "<|EXTRA_88_TOKEN|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "32089": {
743
+ "content": "<|EXTRA_89_TOKEN|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "32090": {
751
+ "content": "<|EXTRA_90_TOKEN|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "32091": {
759
+ "content": "<|EXTRA_91_TOKEN|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "32092": {
767
+ "content": "<|EXTRA_92_TOKEN|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "32093": {
775
+ "content": "<|EXTRA_93_TOKEN|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "32094": {
783
+ "content": "<|EXTRA_94_TOKEN|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "32095": {
791
+ "content": "<|EXTRA_95_TOKEN|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "32096": {
799
+ "content": "<|EXTRA_96_TOKEN|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "32097": {
807
+ "content": "<|EXTRA_97_TOKEN|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "32098": {
815
+ "content": "<|EXTRA_98_TOKEN|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "32099": {
823
+ "content": "<|EXTRA_99_TOKEN|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "32100": {
831
+ "content": "<|EXTRA_100_TOKEN|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "32101": {
839
+ "content": "<|EXTRA_101_TOKEN|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "32102": {
847
+ "content": "<|EXTRA_102_TOKEN|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "32103": {
855
+ "content": "<|EXTRA_103_TOKEN|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "32104": {
863
+ "content": "<|EXTRA_104_TOKEN|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "32105": {
871
+ "content": "<|EXTRA_105_TOKEN|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "32106": {
879
+ "content": "<|EXTRA_106_TOKEN|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "32107": {
887
+ "content": "<|EXTRA_107_TOKEN|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "32108": {
895
+ "content": "<|EXTRA_108_TOKEN|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "32109": {
903
+ "content": "<|EXTRA_109_TOKEN|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "32110": {
911
+ "content": "<|EXTRA_110_TOKEN|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "32111": {
919
+ "content": "<|EXTRA_111_TOKEN|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "32112": {
927
+ "content": "<|EXTRA_112_TOKEN|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "32113": {
935
+ "content": "<|EXTRA_113_TOKEN|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "32114": {
943
+ "content": "<|EXTRA_114_TOKEN|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "32115": {
951
+ "content": "<|EXTRA_115_TOKEN|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "32116": {
959
+ "content": "<|EXTRA_116_TOKEN|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "32117": {
967
+ "content": "<|EXTRA_117_TOKEN|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "32118": {
975
+ "content": "<|EXTRA_118_TOKEN|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "32119": {
983
+ "content": "<|EXTRA_119_TOKEN|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "32120": {
991
+ "content": "<|EXTRA_120_TOKEN|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "32121": {
999
+ "content": "<|EXTRA_121_TOKEN|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "32122": {
1007
+ "content": "<|EXTRA_122_TOKEN|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "32123": {
1015
+ "content": "<|EXTRA_123_TOKEN|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "32124": {
1023
+ "content": "<|EXTRA_124_TOKEN|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "32125": {
1031
+ "content": "<|EXTRA_125_TOKEN|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "32126": {
1039
+ "content": "<|EXTRA_126_TOKEN|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "32127": {
1047
+ "content": "<|EXTRA_127_TOKEN|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ }
1054
+ },
1055
+ "additional_special_tokens": [
1056
+ "<|START_OF_TURN_TOKEN|>",
1057
+ "<|END_OF_TURN_TOKEN|>",
1058
+ "<|USER_TOKEN|>",
1059
+ "<|CHATBOT_TOKEN|>",
1060
+ "<|SYSTEM_TOKEN|>",
1061
+ "<|EXTRA_5_TOKEN|>",
1062
+ "<|EXTRA_6_TOKEN|>",
1063
+ "<|EXTRA_7_TOKEN|>",
1064
+ "<|EXTRA_8_TOKEN|>",
1065
+ "<|EXTRA_9_TOKEN|>",
1066
+ "<|EXTRA_10_TOKEN|>",
1067
+ "<|EXTRA_11_TOKEN|>",
1068
+ "<|EXTRA_12_TOKEN|>",
1069
+ "<|EXTRA_13_TOKEN|>",
1070
+ "<|EXTRA_14_TOKEN|>",
1071
+ "<|EXTRA_15_TOKEN|>",
1072
+ "<|EXTRA_16_TOKEN|>",
1073
+ "<|EXTRA_17_TOKEN|>",
1074
+ "<|EXTRA_18_TOKEN|>",
1075
+ "<|EXTRA_19_TOKEN|>",
1076
+ "<|EXTRA_20_TOKEN|>",
1077
+ "<|EXTRA_21_TOKEN|>",
1078
+ "<|EXTRA_22_TOKEN|>",
1079
+ "<|EXTRA_23_TOKEN|>",
1080
+ "<|EXTRA_24_TOKEN|>",
1081
+ "<|EXTRA_25_TOKEN|>",
1082
+ "<|EXTRA_26_TOKEN|>",
1083
+ "<|EXTRA_27_TOKEN|>",
1084
+ "<|EXTRA_28_TOKEN|>",
1085
+ "<|EXTRA_29_TOKEN|>",
1086
+ "<|EXTRA_30_TOKEN|>",
1087
+ "<|EXTRA_31_TOKEN|>",
1088
+ "<|EXTRA_32_TOKEN|>",
1089
+ "<|EXTRA_33_TOKEN|>",
1090
+ "<|EXTRA_34_TOKEN|>",
1091
+ "<|EXTRA_35_TOKEN|>",
1092
+ "<|EXTRA_36_TOKEN|>",
1093
+ "<|EXTRA_37_TOKEN|>",
1094
+ "<|EXTRA_38_TOKEN|>",
1095
+ "<|EXTRA_39_TOKEN|>",
1096
+ "<|EXTRA_40_TOKEN|>",
1097
+ "<|EXTRA_41_TOKEN|>",
1098
+ "<|EXTRA_42_TOKEN|>",
1099
+ "<|EXTRA_43_TOKEN|>",
1100
+ "<|EXTRA_44_TOKEN|>",
1101
+ "<|EXTRA_45_TOKEN|>",
1102
+ "<|EXTRA_46_TOKEN|>",
1103
+ "<|EXTRA_47_TOKEN|>",
1104
+ "<|EXTRA_48_TOKEN|>",
1105
+ "<|EXTRA_49_TOKEN|>",
1106
+ "<|EXTRA_50_TOKEN|>",
1107
+ "<|EXTRA_51_TOKEN|>",
1108
+ "<|EXTRA_52_TOKEN|>",
1109
+ "<|EXTRA_53_TOKEN|>",
1110
+ "<|EXTRA_54_TOKEN|>",
1111
+ "<|EXTRA_55_TOKEN|>",
1112
+ "<|EXTRA_56_TOKEN|>",
1113
+ "<|EXTRA_57_TOKEN|>",
1114
+ "<|EXTRA_58_TOKEN|>",
1115
+ "<|EXTRA_59_TOKEN|>",
1116
+ "<|EXTRA_60_TOKEN|>",
1117
+ "<|EXTRA_61_TOKEN|>",
1118
+ "<|EXTRA_62_TOKEN|>",
1119
+ "<|EXTRA_63_TOKEN|>",
1120
+ "<|EXTRA_64_TOKEN|>",
1121
+ "<|EXTRA_65_TOKEN|>",
1122
+ "<|EXTRA_66_TOKEN|>",
1123
+ "<|EXTRA_67_TOKEN|>",
1124
+ "<|EXTRA_68_TOKEN|>",
1125
+ "<|EXTRA_69_TOKEN|>",
1126
+ "<|EXTRA_70_TOKEN|>",
1127
+ "<|EXTRA_71_TOKEN|>",
1128
+ "<|EXTRA_72_TOKEN|>",
1129
+ "<|EXTRA_73_TOKEN|>",
1130
+ "<|EXTRA_74_TOKEN|>",
1131
+ "<|EXTRA_75_TOKEN|>",
1132
+ "<|EXTRA_76_TOKEN|>",
1133
+ "<|EXTRA_77_TOKEN|>",
1134
+ "<|EXTRA_78_TOKEN|>",
1135
+ "<|EXTRA_79_TOKEN|>",
1136
+ "<|EXTRA_80_TOKEN|>",
1137
+ "<|EXTRA_81_TOKEN|>",
1138
+ "<|EXTRA_82_TOKEN|>",
1139
+ "<|EXTRA_83_TOKEN|>",
1140
+ "<|EXTRA_84_TOKEN|>",
1141
+ "<|EXTRA_85_TOKEN|>",
1142
+ "<|EXTRA_86_TOKEN|>",
1143
+ "<|EXTRA_87_TOKEN|>",
1144
+ "<|EXTRA_88_TOKEN|>",
1145
+ "<|EXTRA_89_TOKEN|>",
1146
+ "<|EXTRA_90_TOKEN|>",
1147
+ "<|EXTRA_91_TOKEN|>",
1148
+ "<|EXTRA_92_TOKEN|>",
1149
+ "<|EXTRA_93_TOKEN|>",
1150
+ "<|EXTRA_94_TOKEN|>",
1151
+ "<|EXTRA_95_TOKEN|>",
1152
+ "<|EXTRA_96_TOKEN|>",
1153
+ "<|EXTRA_97_TOKEN|>",
1154
+ "<|EXTRA_98_TOKEN|>",
1155
+ "<|EXTRA_99_TOKEN|>",
1156
+ "<|EXTRA_100_TOKEN|>",
1157
+ "<|EXTRA_101_TOKEN|>",
1158
+ "<|EXTRA_102_TOKEN|>",
1159
+ "<|EXTRA_103_TOKEN|>",
1160
+ "<|EXTRA_104_TOKEN|>",
1161
+ "<|EXTRA_105_TOKEN|>",
1162
+ "<|EXTRA_106_TOKEN|>",
1163
+ "<|EXTRA_107_TOKEN|>",
1164
+ "<|EXTRA_108_TOKEN|>",
1165
+ "<|EXTRA_109_TOKEN|>",
1166
+ "<|EXTRA_110_TOKEN|>",
1167
+ "<|EXTRA_111_TOKEN|>",
1168
+ "<|EXTRA_112_TOKEN|>",
1169
+ "<|EXTRA_113_TOKEN|>",
1170
+ "<|EXTRA_114_TOKEN|>",
1171
+ "<|EXTRA_115_TOKEN|>",
1172
+ "<|EXTRA_116_TOKEN|>",
1173
+ "<|EXTRA_117_TOKEN|>",
1174
+ "<|EXTRA_118_TOKEN|>",
1175
+ "<|EXTRA_119_TOKEN|>",
1176
+ "<|EXTRA_120_TOKEN|>",
1177
+ "<|EXTRA_121_TOKEN|>",
1178
+ "<|EXTRA_122_TOKEN|>",
1179
+ "<|EXTRA_123_TOKEN|>",
1180
+ "<|EXTRA_124_TOKEN|>",
1181
+ "<|EXTRA_125_TOKEN|>",
1182
+ "<|EXTRA_126_TOKEN|>",
1183
+ "<|EXTRA_127_TOKEN|>"
1184
+ ],
1185
+ "bos_token": "<s>",
1186
+ "chat_template": [
1187
+ {
1188
+ "name": "default",
1189
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{{ content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{% set helpfulness = helpfulness|string or '4' %}{% set correctness = correctness|string or '4' %}{% set coherence = coherence|string or '4' %}{% set complexity = complexity|string or '4' %}{% set verbosity = verbosity|string or '4' %}{% set quality = quality|string or '4' %}{% set toxicity = toxicity|string or '0' %}{% set humor = humor|string or '0' %}{% set creativity = creativity|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{% endif %}"
1190
+ },
1191
+ {
1192
+ "name": "tool_use",
1193
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# System Instructions' }}{{ '\n## Basic Rules' }}{{ '\nYou are KARAKURI LM, a powerful conversational AI trained by KARAKURI to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Instructions' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{{ '```json\n' }}{{ tools|tojson(indent=2) }}{{ '\n```' }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{{ content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{% set helpfulness = helpfulness|string or '4' %}{% set correctness = correctness|string or '4' %}{% set coherence = coherence|string or '4' %}{% set complexity = complexity|string or '4' %}{% set verbosity = verbosity|string or '4' %}{% set quality = quality|string or '4' %}{% set toxicity = toxicity|string or '0' %}{% set humor = humor|string or '0' %}{% set creativity = creativity|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{% endif %}"
1194
+ },
1195
+ {
1196
+ "name": "rag",
1197
+ "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# System Instructions' }}{{ '\n## Basic Rules' }}{{ '\nYou are KARAKURI LM, a powerful conversational AI trained by KARAKURI to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Instructions' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{% set helpfulness = message['helpfulness']|string or '4' %}{% set correctness = message['correctness']|string or '4' %}{% set coherence = message['coherence']|string or '4' %}{% set complexity = message['complexity']|string or '4' %}{% set verbosity = message['verbosity']|string or '4' %}{% set quality = message['quality']|string or '4' %}{% set toxicity = message['toxicity']|string or '0' %}{% set humor = message['humor']|string or '0' %}{% set creativity = message['creativity']|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{{ content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Write a detailed, high-quality and natural response to the user\\'s last input. Use the retrieved documents to help you.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{% set helpfulness = helpfulness|string or '4' %}{% set correctness = correctness|string or '4' %}{% set coherence = coherence|string or '4' %}{% set complexity = complexity|string or '4' %}{% set verbosity = verbosity|string or '4' %}{% set quality = quality|string or '4' %}{% set toxicity = toxicity|string or '0' %}{% set humor = humor|string or '0' %}{% set creativity = creativity|string or '0' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{{ '<attributes>helpfulness: ' + helpfulness + ' correctness: ' + correctness + ' coherence: ' + coherence + ' complexity: ' + complexity + ' verbosity: ' + verbosity + ' quality: ' + quality + ' toxicity: ' + toxicity + ' humor: ' + humor + ' creativity: ' + creativity + '</attributes>' }}{% endif %}"
1198
+ }
1199
+ ],
1200
+ "clean_up_tokenization_spaces": false,
1201
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
1202
+ "legacy": true,
1203
+ "model_max_length": 1000000000000000019884624838656,
1204
+ "pad_token": null,
1205
+ "sp_model_kwargs": {},
1206
+ "spaces_between_special_tokens": false,
1207
+ "tokenizer_class": "LlamaTokenizer",
1208
+ "unk_token": "<unk>",
1209
+ "use_default_system_prompt": false
1210
+ }