Hugging Face's logo

mlx-community
/
granite-3b-code-instruct-4bit

Text Generation
Transformers
Safetensors
MLX
llama
code
conversational
Eval Results
text-generation-inference
Model card Files Community
1
prince-canuma commited on
Commit
daaaf2a
•
1 Parent(s): d4bd116

718326077b6f24653dc551cf9a8fa6ca6a28e7ea5bf2a1b0e72d11829b3a1777

Browse files
Files changed (9) hide show
  1. README.md +101 -0
  2. config.json +33 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +971 -0
  6. special_tokens_map.json +51 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +188 -0
  9. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - code
6
+ - mlx
7
+ base_model: ibm-granite/granite-3b-code-base
8
+ datasets:
9
+ - bigcode/commitpackft
10
+ - TIGER-Lab/MathInstruct
11
+ - meta-math/MetaMathQA
12
+ - glaiveai/glaive-code-assistant-v3
13
+ - glaive-function-calling-v2
14
+ - bugdaryan/sql-create-context-instruction
15
+ - garage-bAInd/Open-Platypus
16
+ - nvidia/HelpSteer
17
+ metrics:
18
+ - code_eval
19
+ pipeline_tag: text-generation
20
+ inference: false
21
+ model-index:
22
+ - name: granite-3b-code-instruct
23
+ results:
24
+ - task:
25
+ type: text-generation
26
+ dataset:
27
+ name: HumanEvalSynthesis(Python)
28
+ type: bigcode/humanevalpack
29
+ metrics:
30
+ - type: pass@1
31
+ value: 51.2
32
+ name: pass@1
33
+ - type: pass@1
34
+ value: 43.9
35
+ name: pass@1
36
+ - type: pass@1
37
+ value: 41.5
38
+ name: pass@1
39
+ - type: pass@1
40
+ value: 31.7
41
+ name: pass@1
42
+ - type: pass@1
43
+ value: 40.2
44
+ name: pass@1
45
+ - type: pass@1
46
+ value: 29.3
47
+ name: pass@1
48
+ - type: pass@1
49
+ value: 39.6
50
+ name: pass@1
51
+ - type: pass@1
52
+ value: 26.8
53
+ name: pass@1
54
+ - type: pass@1
55
+ value: 39.0
56
+ name: pass@1
57
+ - type: pass@1
58
+ value: 14.0
59
+ name: pass@1
60
+ - type: pass@1
61
+ value: 23.8
62
+ name: pass@1
63
+ - type: pass@1
64
+ value: 12.8
65
+ name: pass@1
66
+ - type: pass@1
67
+ value: 26.8
68
+ name: pass@1
69
+ - type: pass@1
70
+ value: 28.0
71
+ name: pass@1
72
+ - type: pass@1
73
+ value: 33.5
74
+ name: pass@1
75
+ - type: pass@1
76
+ value: 27.4
77
+ name: pass@1
78
+ - type: pass@1
79
+ value: 31.7
80
+ name: pass@1
81
+ - type: pass@1
82
+ value: 16.5
83
+ name: pass@1
84
+ ---
85
+
86
+ # mlx-community/granite-3b-code-instruct-4bit
87
+
88
+ The Model [mlx-community/granite-3b-code-instruct-4bit](https://huggingface.co/mlx-community/granite-3b-code-instruct-4bit) was converted to MLX format from [ibm-granite/granite-3b-code-instruct](https://huggingface.co/ibm-granite/granite-3b-code-instruct) using mlx-lm version **0.12.0**.
89
+
90
+ ## Use with mlx
91
+
92
+ ```bash
93
+ pip install mlx-lm
94
+ ```
95
+
96
+ ```python
97
+ from mlx_lm import load, generate
98
+
99
+ model, tokenizer = load("mlx-community/granite-3b-code-instruct-4bit")
100
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
101
+ ```
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2560,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 10240,
13
+ "max_position_embeddings": 2048,
14
+ "mlp_bias": true,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "quantization": {
22
+ "group_size": 64,
23
+ "bits": 4
24
+ },
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.41.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 49152
33
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88f5cb1d7ca721f178dde6f9e8121893c14d1e430608510855f13b7f2f39687
3
+ size 1960785871
model.safetensors.index.json ADDED
@@ -0,0 +1,971 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1960678400
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.biases": "model.safetensors",
7
+ "model.embed_tokens.scales": "model.safetensors",
8
+ "model.embed_tokens.weight": "model.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
10
+ "model.layers.0.mlp.down_proj.bias": "model.safetensors",
11
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
12
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
14
+ "model.layers.0.mlp.gate_proj.bias": "model.safetensors",
15
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
16
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
17
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
18
+ "model.layers.0.mlp.up_proj.bias": "model.safetensors",
19
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
20
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
21
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
22
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
23
+ "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
24
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
25
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
26
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
27
+ "model.layers.0.self_attn.o_proj.bias": "model.safetensors",
28
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
29
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
30
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
31
+ "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
32
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
33
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
34
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
35
+ "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
36
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
37
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
38
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
39
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
40
+ "model.layers.1.mlp.down_proj.bias": "model.safetensors",
41
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
42
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
43
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
44
+ "model.layers.1.mlp.gate_proj.bias": "model.safetensors",
45
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
46
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
47
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
48
+ "model.layers.1.mlp.up_proj.bias": "model.safetensors",
49
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
50
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
51
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
52
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
53
+ "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
54
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
55
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
56
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
57
+ "model.layers.1.self_attn.o_proj.bias": "model.safetensors",
58
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
59
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
60
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
61
+ "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
62
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
63
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
64
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
65
+ "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
66
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
67
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
68
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
69
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
70
+ "model.layers.10.mlp.down_proj.bias": "model.safetensors",
71
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
72
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
73
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
74
+ "model.layers.10.mlp.gate_proj.bias": "model.safetensors",
75
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
76
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
77
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
78
+ "model.layers.10.mlp.up_proj.bias": "model.safetensors",
79
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
80
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
81
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
82
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
83
+ "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
84
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
85
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
86
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
87
+ "model.layers.10.self_attn.o_proj.bias": "model.safetensors",
88
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
89
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
90
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
91
+ "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
92
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
93
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
94
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
95
+ "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
96
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
97
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
98
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
99
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
100
+ "model.layers.11.mlp.down_proj.bias": "model.safetensors",
101
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
102
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
103
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
104
+ "model.layers.11.mlp.gate_proj.bias": "model.safetensors",
105
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
106
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
107
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
108
+ "model.layers.11.mlp.up_proj.bias": "model.safetensors",
109
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
110
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
111
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
112
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
113
+ "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
114
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
115
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
116
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
117
+ "model.layers.11.self_attn.o_proj.bias": "model.safetensors",
118
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
119
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
120
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
121
+ "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
122
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
123
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
124
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
125
+ "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
126
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
127
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
128
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
129
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
130
+ "model.layers.12.mlp.down_proj.bias": "model.safetensors",
131
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
132
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
133
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
134
+ "model.layers.12.mlp.gate_proj.bias": "model.safetensors",
135
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
136
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
137
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
138
+ "model.layers.12.mlp.up_proj.bias": "model.safetensors",
139
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
140
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
141
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
142
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
143
+ "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
144
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
145
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
146
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
147
+ "model.layers.12.self_attn.o_proj.bias": "model.safetensors",
148
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
149
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
150
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
151
+ "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
152
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
153
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
154
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
155
+ "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
156
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
157
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
158
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
159
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
160
+ "model.layers.13.mlp.down_proj.bias": "model.safetensors",
161
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
162
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
163
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
164
+ "model.layers.13.mlp.gate_proj.bias": "model.safetensors",
165
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
166
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
167
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
168
+ "model.layers.13.mlp.up_proj.bias": "model.safetensors",
169
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
170
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
171
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
172
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
173
+ "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
174
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
175
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
176
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
177
+ "model.layers.13.self_attn.o_proj.bias": "model.safetensors",
178
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
179
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
180
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
181
+ "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
182
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
183
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
184
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
185
+ "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
186
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
187
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
188
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
189
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
190
+ "model.layers.14.mlp.down_proj.bias": "model.safetensors",
191
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
192
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
193
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
194
+ "model.layers.14.mlp.gate_proj.bias": "model.safetensors",
195
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
196
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
197
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
198
+ "model.layers.14.mlp.up_proj.bias": "model.safetensors",
199
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
200
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
201
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
202
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
203
+ "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
204
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
205
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
206
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
207
+ "model.layers.14.self_attn.o_proj.bias": "model.safetensors",
208
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
209
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
210
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
211
+ "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
212
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
213
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
214
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
215
+ "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
216
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
217
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
218
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
219
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
220
+ "model.layers.15.mlp.down_proj.bias": "model.safetensors",
221
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
222
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
223
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
224
+ "model.layers.15.mlp.gate_proj.bias": "model.safetensors",
225
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
226
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
227
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
228
+ "model.layers.15.mlp.up_proj.bias": "model.safetensors",
229
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
230
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
231
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
232
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
233
+ "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
234
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
235
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
236
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
237
+ "model.layers.15.self_attn.o_proj.bias": "model.safetensors",
238
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
239
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
240
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
241
+ "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
242
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
243
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
244
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
245
+ "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
246
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
247
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
248
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
249
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
250
+ "model.layers.16.mlp.down_proj.bias": "model.safetensors",
251
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
252
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
253
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
254
+ "model.layers.16.mlp.gate_proj.bias": "model.safetensors",
255
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
256
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
257
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
258
+ "model.layers.16.mlp.up_proj.bias": "model.safetensors",
259
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
260
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
261
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
262
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
263
+ "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
264
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
265
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
266
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
267
+ "model.layers.16.self_attn.o_proj.bias": "model.safetensors",
268
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
269
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
270
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
271
+ "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
272
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
273
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
274
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
275
+ "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
276
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
277
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
278
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
279
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
280
+ "model.layers.17.mlp.down_proj.bias": "model.safetensors",
281
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
282
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
283
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
284
+ "model.layers.17.mlp.gate_proj.bias": "model.safetensors",
285
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
286
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
287
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
288
+ "model.layers.17.mlp.up_proj.bias": "model.safetensors",
289
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
290
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
291
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
292
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
293
+ "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
294
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
295
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
296
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
297
+ "model.layers.17.self_attn.o_proj.bias": "model.safetensors",
298
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
299
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
300
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
301
+ "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
302
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
303
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
304
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
305
+ "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
306
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
310
+ "model.layers.18.mlp.down_proj.bias": "model.safetensors",
311
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
312
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
313
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
314
+ "model.layers.18.mlp.gate_proj.bias": "model.safetensors",
315
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
316
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
317
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
318
+ "model.layers.18.mlp.up_proj.bias": "model.safetensors",
319
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
320
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
321
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
322
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
323
+ "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
324
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
325
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
326
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
327
+ "model.layers.18.self_attn.o_proj.bias": "model.safetensors",
328
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
329
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
330
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
331
+ "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
332
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
333
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
334
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
335
+ "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
336
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
337
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
338
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
339
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
340
+ "model.layers.19.mlp.down_proj.bias": "model.safetensors",
341
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
342
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
343
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
344
+ "model.layers.19.mlp.gate_proj.bias": "model.safetensors",
345
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
346
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
347
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
348
+ "model.layers.19.mlp.up_proj.bias": "model.safetensors",
349
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
350
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
351
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
352
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
353
+ "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
354
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
355
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
356
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
357
+ "model.layers.19.self_attn.o_proj.bias": "model.safetensors",
358
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
359
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
360
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
361
+ "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
362
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
363
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
364
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
365
+ "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
366
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
367
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
368
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
369
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
370
+ "model.layers.2.mlp.down_proj.bias": "model.safetensors",
371
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
372
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
373
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
374
+ "model.layers.2.mlp.gate_proj.bias": "model.safetensors",
375
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
376
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
377
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
378
+ "model.layers.2.mlp.up_proj.bias": "model.safetensors",
379
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
380
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
381
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
382
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
383
+ "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
384
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
385
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
386
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
387
+ "model.layers.2.self_attn.o_proj.bias": "model.safetensors",
388
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
389
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
390
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
391
+ "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
392
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
393
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
394
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
395
+ "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
396
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
397
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
398
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
399
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
400
+ "model.layers.20.mlp.down_proj.bias": "model.safetensors",
401
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
402
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
403
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
404
+ "model.layers.20.mlp.gate_proj.bias": "model.safetensors",
405
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
406
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
407
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
408
+ "model.layers.20.mlp.up_proj.bias": "model.safetensors",
409
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
410
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
411
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
412
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
413
+ "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
414
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
415
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
416
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
417
+ "model.layers.20.self_attn.o_proj.bias": "model.safetensors",
418
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
419
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
420
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
421
+ "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
422
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
423
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
424
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
425
+ "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
426
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
427
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
428
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
429
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
430
+ "model.layers.21.mlp.down_proj.bias": "model.safetensors",
431
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
432
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
433
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
434
+ "model.layers.21.mlp.gate_proj.bias": "model.safetensors",
435
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
436
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
437
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
438
+ "model.layers.21.mlp.up_proj.bias": "model.safetensors",
439
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
440
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
441
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
442
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
443
+ "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
444
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
445
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
446
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
447
+ "model.layers.21.self_attn.o_proj.bias": "model.safetensors",
448
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
449
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
450
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
451
+ "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
452
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
453
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
454
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
455
+ "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
456
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
457
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
458
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
459
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
460
+ "model.layers.22.mlp.down_proj.bias": "model.safetensors",
461
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
462
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
463
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
464
+ "model.layers.22.mlp.gate_proj.bias": "model.safetensors",
465
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
466
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
467
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
468
+ "model.layers.22.mlp.up_proj.bias": "model.safetensors",
469
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
470
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
471
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
472
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
473
+ "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
474
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
475
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
476
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
477
+ "model.layers.22.self_attn.o_proj.bias": "model.safetensors",
478
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
479
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
480
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
481
+ "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
482
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
483
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
484
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
485
+ "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
486
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
487
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
488
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
489
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
490
+ "model.layers.23.mlp.down_proj.bias": "model.safetensors",
491
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
492
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
493
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
494
+ "model.layers.23.mlp.gate_proj.bias": "model.safetensors",
495
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
496
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
497
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
498
+ "model.layers.23.mlp.up_proj.bias": "model.safetensors",
499
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
500
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
501
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
502
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
503
+ "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
504
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
505
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
506
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
507
+ "model.layers.23.self_attn.o_proj.bias": "model.safetensors",
508
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
509
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
510
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
511
+ "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
512
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
513
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
514
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
515
+ "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
516
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
517
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
518
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
519
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
520
+ "model.layers.24.mlp.down_proj.bias": "model.safetensors",
521
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
522
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
523
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
524
+ "model.layers.24.mlp.gate_proj.bias": "model.safetensors",
525
+ "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
526
+ "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
527
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
528
+ "model.layers.24.mlp.up_proj.bias": "model.safetensors",
529
+ "model.layers.24.mlp.up_proj.biases": "model.safetensors",
530
+ "model.layers.24.mlp.up_proj.scales": "model.safetensors",
531
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
532
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
533
+ "model.layers.24.self_attn.k_proj.bias": "model.safetensors",
534
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
535
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
536
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
537
+ "model.layers.24.self_attn.o_proj.bias": "model.safetensors",
538
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
539
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
540
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
541
+ "model.layers.24.self_attn.q_proj.bias": "model.safetensors",
542
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
543
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
544
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
545
+ "model.layers.24.self_attn.v_proj.bias": "model.safetensors",
546
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
547
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
548
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
549
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
550
+ "model.layers.25.mlp.down_proj.bias": "model.safetensors",
551
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
552
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
553
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
554
+ "model.layers.25.mlp.gate_proj.bias": "model.safetensors",
555
+ "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
556
+ "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
557
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
558
+ "model.layers.25.mlp.up_proj.bias": "model.safetensors",
559
+ "model.layers.25.mlp.up_proj.biases": "model.safetensors",
560
+ "model.layers.25.mlp.up_proj.scales": "model.safetensors",
561
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
562
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
563
+ "model.layers.25.self_attn.k_proj.bias": "model.safetensors",
564
+ "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
565
+ "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
566
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
567
+ "model.layers.25.self_attn.o_proj.bias": "model.safetensors",
568
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
569
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
570
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
571
+ "model.layers.25.self_attn.q_proj.bias": "model.safetensors",
572
+ "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
573
+ "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
574
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
575
+ "model.layers.25.self_attn.v_proj.bias": "model.safetensors",
576
+ "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
577
+ "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
578
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
579
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
580
+ "model.layers.26.mlp.down_proj.bias": "model.safetensors",
581
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
582
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
583
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
584
+ "model.layers.26.mlp.gate_proj.bias": "model.safetensors",
585
+ "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
586
+ "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
587
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
588
+ "model.layers.26.mlp.up_proj.bias": "model.safetensors",
589
+ "model.layers.26.mlp.up_proj.biases": "model.safetensors",
590
+ "model.layers.26.mlp.up_proj.scales": "model.safetensors",
591
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
592
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
593
+ "model.layers.26.self_attn.k_proj.bias": "model.safetensors",
594
+ "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
595
+ "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
596
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
597
+ "model.layers.26.self_attn.o_proj.bias": "model.safetensors",
598
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
599
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
600
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
601
+ "model.layers.26.self_attn.q_proj.bias": "model.safetensors",
602
+ "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
603
+ "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
604
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
605
+ "model.layers.26.self_attn.v_proj.bias": "model.safetensors",
606
+ "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
607
+ "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
608
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
609
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
610
+ "model.layers.27.mlp.down_proj.bias": "model.safetensors",
611
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
612
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
613
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
614
+ "model.layers.27.mlp.gate_proj.bias": "model.safetensors",
615
+ "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
616
+ "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
617
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
618
+ "model.layers.27.mlp.up_proj.bias": "model.safetensors",
619
+ "model.layers.27.mlp.up_proj.biases": "model.safetensors",
620
+ "model.layers.27.mlp.up_proj.scales": "model.safetensors",
621
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
622
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
623
+ "model.layers.27.self_attn.k_proj.bias": "model.safetensors",
624
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
625
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
626
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
627
+ "model.layers.27.self_attn.o_proj.bias": "model.safetensors",
628
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
629
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
630
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
631
+ "model.layers.27.self_attn.q_proj.bias": "model.safetensors",
632
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
633
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
634
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
635
+ "model.layers.27.self_attn.v_proj.bias": "model.safetensors",
636
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
637
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
638
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
639
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
640
+ "model.layers.28.mlp.down_proj.bias": "model.safetensors",
641
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
642
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
643
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
644
+ "model.layers.28.mlp.gate_proj.bias": "model.safetensors",
645
+ "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
646
+ "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
647
+ "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
648
+ "model.layers.28.mlp.up_proj.bias": "model.safetensors",
649
+ "model.layers.28.mlp.up_proj.biases": "model.safetensors",
650
+ "model.layers.28.mlp.up_proj.scales": "model.safetensors",
651
+ "model.layers.28.mlp.up_proj.weight": "model.safetensors",
652
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
653
+ "model.layers.28.self_attn.k_proj.bias": "model.safetensors",
654
+ "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
655
+ "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
656
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
657
+ "model.layers.28.self_attn.o_proj.bias": "model.safetensors",
658
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
659
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
660
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
661
+ "model.layers.28.self_attn.q_proj.bias": "model.safetensors",
662
+ "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
663
+ "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
664
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
665
+ "model.layers.28.self_attn.v_proj.bias": "model.safetensors",
666
+ "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
667
+ "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
668
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
669
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
670
+ "model.layers.29.mlp.down_proj.bias": "model.safetensors",
671
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
672
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
673
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
674
+ "model.layers.29.mlp.gate_proj.bias": "model.safetensors",
675
+ "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
676
+ "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
677
+ "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
678
+ "model.layers.29.mlp.up_proj.bias": "model.safetensors",
679
+ "model.layers.29.mlp.up_proj.biases": "model.safetensors",
680
+ "model.layers.29.mlp.up_proj.scales": "model.safetensors",
681
+ "model.layers.29.mlp.up_proj.weight": "model.safetensors",
682
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
683
+ "model.layers.29.self_attn.k_proj.bias": "model.safetensors",
684
+ "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
685
+ "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
686
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
687
+ "model.layers.29.self_attn.o_proj.bias": "model.safetensors",
688
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
689
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
690
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
691
+ "model.layers.29.self_attn.q_proj.bias": "model.safetensors",
692
+ "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
693
+ "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
694
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
695
+ "model.layers.29.self_attn.v_proj.bias": "model.safetensors",
696
+ "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
697
+ "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
698
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
699
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
700
+ "model.layers.3.mlp.down_proj.bias": "model.safetensors",
701
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
702
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
703
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
704
+ "model.layers.3.mlp.gate_proj.bias": "model.safetensors",
705
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
706
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
707
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
708
+ "model.layers.3.mlp.up_proj.bias": "model.safetensors",
709
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
710
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
711
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
712
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
713
+ "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
714
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
715
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
716
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
717
+ "model.layers.3.self_attn.o_proj.bias": "model.safetensors",
718
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
719
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
720
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
721
+ "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
722
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
723
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
724
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
725
+ "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
726
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
727
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
728
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
729
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
730
+ "model.layers.30.mlp.down_proj.bias": "model.safetensors",
731
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
732
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
733
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
734
+ "model.layers.30.mlp.gate_proj.bias": "model.safetensors",
735
+ "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
736
+ "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
737
+ "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
738
+ "model.layers.30.mlp.up_proj.bias": "model.safetensors",
739
+ "model.layers.30.mlp.up_proj.biases": "model.safetensors",
740
+ "model.layers.30.mlp.up_proj.scales": "model.safetensors",
741
+ "model.layers.30.mlp.up_proj.weight": "model.safetensors",
742
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
743
+ "model.layers.30.self_attn.k_proj.bias": "model.safetensors",
744
+ "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
745
+ "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
746
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
747
+ "model.layers.30.self_attn.o_proj.bias": "model.safetensors",
748
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
749
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
750
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
751
+ "model.layers.30.self_attn.q_proj.bias": "model.safetensors",
752
+ "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
753
+ "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
754
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
755
+ "model.layers.30.self_attn.v_proj.bias": "model.safetensors",
756
+ "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
757
+ "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
758
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
759
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
760
+ "model.layers.31.mlp.down_proj.bias": "model.safetensors",
761
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
762
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
763
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
764
+ "model.layers.31.mlp.gate_proj.bias": "model.safetensors",
765
+ "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
766
+ "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
767
+ "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
768
+ "model.layers.31.mlp.up_proj.bias": "model.safetensors",
769
+ "model.layers.31.mlp.up_proj.biases": "model.safetensors",
770
+ "model.layers.31.mlp.up_proj.scales": "model.safetensors",
771
+ "model.layers.31.mlp.up_proj.weight": "model.safetensors",
772
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
773
+ "model.layers.31.self_attn.k_proj.bias": "model.safetensors",
774
+ "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
775
+ "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
776
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
777
+ "model.layers.31.self_attn.o_proj.bias": "model.safetensors",
778
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
779
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
780
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
781
+ "model.layers.31.self_attn.q_proj.bias": "model.safetensors",
782
+ "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
783
+ "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
784
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
785
+ "model.layers.31.self_attn.v_proj.bias": "model.safetensors",
786
+ "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
787
+ "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
788
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
789
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
790
+ "model.layers.4.mlp.down_proj.bias": "model.safetensors",
791
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
792
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
793
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
794
+ "model.layers.4.mlp.gate_proj.bias": "model.safetensors",
795
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
796
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
797
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
798
+ "model.layers.4.mlp.up_proj.bias": "model.safetensors",
799
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
800
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
801
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
802
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
803
+ "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
804
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
805
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
806
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
807
+ "model.layers.4.self_attn.o_proj.bias": "model.safetensors",
808
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
809
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
810
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
811
+ "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
812
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
813
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
814
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
815
+ "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
816
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
817
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
818
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
819
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
820
+ "model.layers.5.mlp.down_proj.bias": "model.safetensors",
821
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
822
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
823
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
824
+ "model.layers.5.mlp.gate_proj.bias": "model.safetensors",
825
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
826
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
827
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
828
+ "model.layers.5.mlp.up_proj.bias": "model.safetensors",
829
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
830
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
831
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
832
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
833
+ "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
834
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
835
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
836
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
837
+ "model.layers.5.self_attn.o_proj.bias": "model.safetensors",
838
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
839
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
840
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
841
+ "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
842
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
843
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
844
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
845
+ "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
846
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
847
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
848
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
849
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
850
+ "model.layers.6.mlp.down_proj.bias": "model.safetensors",
851
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
852
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
853
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
854
+ "model.layers.6.mlp.gate_proj.bias": "model.safetensors",
855
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
856
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
857
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
858
+ "model.layers.6.mlp.up_proj.bias": "model.safetensors",
859
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
860
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
861
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
862
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
863
+ "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
864
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
865
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
866
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
867
+ "model.layers.6.self_attn.o_proj.bias": "model.safetensors",
868
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
869
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
870
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
871
+ "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
872
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
873
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
874
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
875
+ "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
876
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
877
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
878
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
879
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
880
+ "model.layers.7.mlp.down_proj.bias": "model.safetensors",
881
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
882
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
883
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
884
+ "model.layers.7.mlp.gate_proj.bias": "model.safetensors",
885
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
886
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
887
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
888
+ "model.layers.7.mlp.up_proj.bias": "model.safetensors",
889
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
890
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
891
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
892
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
893
+ "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
894
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
895
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
896
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
897
+ "model.layers.7.self_attn.o_proj.bias": "model.safetensors",
898
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
899
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
900
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
901
+ "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
902
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
903
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
904
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
905
+ "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
906
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
907
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
908
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
909
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
910
+ "model.layers.8.mlp.down_proj.bias": "model.safetensors",
911
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
912
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
913
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
914
+ "model.layers.8.mlp.gate_proj.bias": "model.safetensors",
915
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
916
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
917
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
918
+ "model.layers.8.mlp.up_proj.bias": "model.safetensors",
919
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
920
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
921
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
922
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
923
+ "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
924
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
925
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
926
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
927
+ "model.layers.8.self_attn.o_proj.bias": "model.safetensors",
928
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
929
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
930
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
931
+ "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
932
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
933
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
934
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
935
+ "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
936
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
937
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
938
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
939
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
940
+ "model.layers.9.mlp.down_proj.bias": "model.safetensors",
941
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
942
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
943
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
944
+ "model.layers.9.mlp.gate_proj.bias": "model.safetensors",
945
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
946
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
947
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
948
+ "model.layers.9.mlp.up_proj.bias": "model.safetensors",
949
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
950
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
951
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
952
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
953
+ "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
954
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
955
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
956
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
957
+ "model.layers.9.self_attn.o_proj.bias": "model.safetensors",
958
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
959
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
960
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
961
+ "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
962
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
963
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
964
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
965
+ "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
966
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
967
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
968
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
969
+ "model.norm.weight": "model.safetensors"
970
+ }
971
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n' + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
180
+ "clean_up_tokenization_spaces": true,
181
+ "eos_token": "<|endoftext|>",
182
+ "model_max_length": 9223372036854775807,
183
+ "pad_token": "<|endoftext|>",
184
+ "padding_side": "left",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff