mlabonne commited on
Commit
857806b
1 Parent(s): 9e2f44d

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257,
40
+ "<|im_end|>": 50295,
41
+ "<|im_start|>": 50296
42
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2_6-phi-2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "MixtralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attn_pdrop": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "cognitivecomputations/dolphin-2_6-phi-2--configuration_phi.PhiConfig",
11
+ "AutoModelForCausalLM": "cognitivecomputations/dolphin-2_6-phi-2--modeling_phi.PhiForCausalLM"
12
+ },
13
+ "bos_token_id": null,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": null,
16
+ "flash_attn": false,
17
+ "flash_rotary": false,
18
+ "fused_dense": false,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 4096,
21
+ "img_processor": null,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 14336,
24
+ "layer_norm_epsilon": 1e-05,
25
+ "max_position_embeddings": 2048,
26
+ "model_type": "mixtral",
27
+ "n_embd": 2560,
28
+ "n_head": 32,
29
+ "n_head_kv": null,
30
+ "n_inner": null,
31
+ "n_layer": 32,
32
+ "n_positions": 2048,
33
+ "num_attention_heads": 32,
34
+ "num_experts_per_tok": 2,
35
+ "num_hidden_layers": 32,
36
+ "num_key_value_heads": 8,
37
+ "num_local_experts": 2,
38
+ "output_router_logits": false,
39
+ "resid_pdrop": 0.1,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_theta": 10000.0,
42
+ "rotary_dim": 32,
43
+ "router_aux_loss_coef": 0.001,
44
+ "sliding_window": null,
45
+ "tie_word_embeddings": false,
46
+ "torch_dtype": "float16",
47
+ "transformers_version": "4.36.2",
48
+ "use_cache": false,
49
+ "vocab_size": 51200
50
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ base_model: cognitivecomputations/dolphin-2_6-phi-2
2
+ gate_mode: cheap_embed
3
+ experts:
4
+ - source_model: cognitivecomputations/dolphin-2_6-phi-2
5
+ positive_prompts: [""]
6
+ - source_model: mrm8488/phi-2-coder
7
+ positive_prompts: [""]
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c818875d84b285b8cb1b904d9b8a71a03acdbaa684ef8a5777a4d660409cb0d
3
+ size 8916015136
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embd.wte.weight": "model-00001-of-00001.safetensors", "lm_head.linear.bias": "model-00001-of-00001.safetensors", "lm_head.linear.weight": "model-00001-of-00001.safetensors", "lm_head.ln.bias": "model-00001-of-00001.safetensors", "lm_head.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.20.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.21.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.22.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.23.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.24.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.25.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.26.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.27.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.28.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.29.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.30.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.31.ln.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.20.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.21.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.22.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.23.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.24.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.25.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.26.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.27.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.28.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.29.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.30.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.31.ln.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.24.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.25.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.26.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.27.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.28.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.29.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.30.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "transformer.h.31.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,341 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50295": {
317
+ "content": "<|im_end|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50296": {
325
+ "content": "<|im_start|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ }
332
+ },
333
+ "bos_token": "<|endoftext|>",
334
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
335
+ "clean_up_tokenization_spaces": true,
336
+ "eos_token": "<|im_end|>",
337
+ "model_max_length": 2048,
338
+ "pad_token": "<|endoftext|>",
339
+ "tokenizer_class": "CodeGenTokenizer",
340
+ "unk_token": "<|endoftext|>"
341
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff