Hugging Face's logo

TroyDoesAI
/
JunkExperiment

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files Community
TroyDoesAI commited on
Commit
8f296bf
·
verified ·
1 Parent(s): e851106

Very Experimental: Dont Expect Much, This is under 6GB in 4bit.

Browse files
Files changed (10) hide show
  1. config.json +10 -15
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +2 -2
  6. model.safetensors.index.json +256 -628
  7. special_tokens_map.json +5 -5
  8. tokenizer.json +0 -0
  9. tokenizer.model +2 -2
  10. tokenizer_config.json +18 -14
config.json CHANGED
@@ -1,34 +1,29 @@
1
  {
2
  "_name_or_path": ".\\Mermaid\\",
3
  "architectures": [
4
- "MixtralForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
- "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 11008,
14
  "max_position_embeddings": 4096,
15
- "model_type": "mixtral",
16
- "num_attention_heads": 32,
17
- "num_experts_per_tok": 2,
18
- "num_hidden_layers": 48,
19
- "num_key_value_heads": 4,
20
- "num_local_experts": 2,
21
- "output_router_logits": false,
22
  "pad_token_id": 0,
23
  "pretraining_tp": 1,
24
- "rms_norm_eps": 1e-06,
25
  "rope_scaling": null,
26
- "rope_theta": 10000,
27
- "router_aux_loss_coef": 0.001,
28
- "sliding_window": null,
29
  "tie_word_embeddings": false,
30
  "torch_dtype": "float16",
31
  "transformers_version": "4.37.2",
32
  "use_cache": true,
33
- "vocab_size": 64000
34
  }
 
1
  {
2
  "_name_or_path": ".\\Mermaid\\",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
  "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 40,
 
 
 
19
  "pad_token_id": 0,
20
  "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
+ "rope_theta": 10000.0,
 
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float16",
26
  "transformers_version": "4.37.2",
27
  "use_cache": true,
28
+ "vocab_size": 32032
29
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf859161d2b8a68e45fa9f2367ee0b62c07897c47e6bd61597988b6ff7846faf
3
  size 4978593408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:958873bdcaa8b4a4c70037aacd743a7cae1ba301efc53f209d8d67d2d1ec3983
3
  size 4978593408
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4a40e177a91dbc5f5131f2ab1df39160a63197166c05f01a5319f527b2e2ee6
3
  size 4970422160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b4bf3ad809db2495e310687c43190548913343594026258fac0894dcb8ce05
3
  size 4970422160
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869138685341403ea41ae9e0d7b6b2974238387dba82a33fd88c45e0bb7a7559
3
  size 4970422184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4360990ea817f89a2e1170526d229b690f4d38cc059c7233c04588d97c730c
3
  size 4970422184
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eadc28e80ecacf2a4dddd472cb2840c797cd80819b1827327fd5a24124256604
3
- size 2231248120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2857227003c5e68faf23a426305dfc7669cbe5c0abe5371088985647078542
3
+ size 3500068128
model.safetensors.index.json CHANGED
@@ -1,634 +1,262 @@
1
  {
2
  "metadata": {
3
- "total_size": 30645166080
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00007-of-00007.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
- "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
9
- "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
10
- "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
11
- "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
12
- "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
13
- "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
14
- "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
15
- "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
16
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
17
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
18
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
19
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
20
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
- "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
22
- "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
23
- "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
24
- "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
25
- "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
26
- "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
27
- "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
28
- "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
29
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
30
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
31
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
32
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
33
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
34
- "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
35
- "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
36
- "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
37
- "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
38
- "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
39
- "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
40
- "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
41
- "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
42
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
43
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
44
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
45
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
46
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
47
- "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
48
- "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
49
- "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
50
- "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
51
- "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
52
- "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
53
- "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
54
- "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
55
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
56
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
57
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
58
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
59
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
60
- "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
61
- "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
62
- "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
63
- "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
64
- "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
65
- "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
66
- "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
67
- "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
68
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
69
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
70
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
71
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
72
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
73
- "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
74
- "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
75
- "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
76
- "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
77
- "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
78
- "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
79
- "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
80
- "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
81
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
82
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
83
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
84
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
85
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
86
- "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
87
- "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
88
- "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
89
- "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
90
- "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
91
- "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
92
- "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
93
- "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
94
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
95
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
96
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
97
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
98
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
99
- "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
100
- "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
101
- "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
102
- "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
103
- "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
104
- "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
105
- "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
106
- "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
107
- "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
108
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
109
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
110
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
111
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
112
- "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
113
- "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
114
- "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
115
- "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
116
- "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
117
- "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
118
- "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
119
- "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
120
- "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
121
- "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
122
- "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
123
- "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
124
- "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
125
- "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
126
- "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
127
- "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
128
- "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
129
- "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
130
- "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
131
- "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
132
- "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
133
- "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
134
- "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
135
- "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
136
- "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
137
- "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
138
- "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
139
- "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
140
- "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
141
- "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
142
- "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
143
- "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
144
- "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
145
- "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
146
- "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
147
- "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
148
- "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
149
- "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
150
- "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
151
- "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
152
- "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
153
- "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
154
- "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
155
- "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
156
- "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
157
- "model.layers.19.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
158
- "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
159
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
160
- "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
161
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
162
- "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
163
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
164
- "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
165
- "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
166
- "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
167
- "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
168
- "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
169
- "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
170
- "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
171
- "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
172
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
173
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
174
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
175
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
176
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
177
- "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
178
- "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
179
- "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
180
- "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
181
- "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
182
- "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
183
- "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
184
- "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
185
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
186
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
187
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
188
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
189
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
190
- "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
191
- "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
192
- "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
193
- "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
194
- "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
195
- "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
196
- "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
197
- "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
198
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
199
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
200
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
201
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
202
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
203
- "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
204
- "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
205
- "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
206
- "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
207
- "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
208
- "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
209
- "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
210
- "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
211
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
212
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
213
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
214
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
215
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
216
- "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
217
- "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
218
- "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
219
- "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
220
- "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
221
- "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
222
- "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
223
- "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
224
- "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
225
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
226
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
227
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
228
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
229
- "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
230
- "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
231
- "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
232
- "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
233
- "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
234
- "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
235
- "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
236
- "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
237
- "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
238
- "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
239
- "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
240
- "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
241
- "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
242
- "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
243
- "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
244
- "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
245
- "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
246
- "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
247
- "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
248
- "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
249
- "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
250
- "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
251
- "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
252
- "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
253
- "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
254
- "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
255
- "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
256
- "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
257
- "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
258
- "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
259
- "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
260
- "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
261
- "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
262
- "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
263
- "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
264
- "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
265
- "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
266
- "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
267
- "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
268
- "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
269
- "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
270
- "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
271
- "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
272
- "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
273
- "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
274
- "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
275
- "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
276
- "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
277
- "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
278
- "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
279
- "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
280
- "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
281
- "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
282
- "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
283
- "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
284
- "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
285
- "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
286
- "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
287
- "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
288
- "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
289
- "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
290
- "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
291
- "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
292
- "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
293
- "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
294
- "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
295
- "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
296
- "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
297
- "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
298
- "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
299
- "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
300
- "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
301
- "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
302
- "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
303
- "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
304
- "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
305
- "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
306
- "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
307
- "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
308
- "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
309
- "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
310
- "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
311
- "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
312
- "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
313
- "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
314
- "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
315
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
316
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
317
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
318
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
319
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
320
- "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
321
- "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
322
- "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
323
- "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
324
- "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
325
- "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
326
- "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
327
- "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
328
- "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
329
- "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
330
- "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
331
- "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
332
- "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
333
- "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
334
- "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
335
- "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
336
- "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
337
- "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
338
- "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
339
- "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
340
- "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
341
- "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
342
- "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
343
- "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
344
- "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
345
- "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
346
- "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
347
- "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
348
- "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
349
- "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
350
- "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
351
- "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
352
- "model.layers.32.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
353
- "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
354
- "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
355
- "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
356
- "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
357
- "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
358
- "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
359
- "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
360
- "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
361
- "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
362
- "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
363
- "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
364
- "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
365
- "model.layers.33.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
366
- "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
367
- "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
368
- "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
369
- "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
370
- "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
371
- "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
372
- "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
373
- "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
374
- "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
375
- "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
376
- "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
377
- "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
378
- "model.layers.34.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
379
- "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
380
- "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
381
- "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
382
- "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
383
- "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
384
- "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
385
- "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
386
- "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
387
- "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
388
- "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
389
- "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
390
- "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
391
- "model.layers.35.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
392
- "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
393
- "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
394
- "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
395
- "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
396
- "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
397
- "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
398
- "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
399
- "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
400
- "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
401
- "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
402
- "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
403
- "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
404
- "model.layers.36.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
405
- "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
406
- "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
407
- "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
408
- "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
409
- "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
410
- "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
411
- "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
412
- "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
413
- "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
414
- "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
415
- "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
416
- "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
417
- "model.layers.37.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
418
- "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
419
- "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
420
- "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
421
- "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
422
- "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
423
- "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
424
- "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
425
- "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
426
- "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
427
- "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
428
- "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
429
- "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
430
- "model.layers.38.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
431
- "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
432
- "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
433
- "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
434
- "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
435
- "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
436
- "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
437
- "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
438
- "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
439
- "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
440
- "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
441
- "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
442
- "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
443
- "model.layers.39.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
444
- "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
445
- "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
446
- "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
447
- "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
448
- "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
449
- "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
450
- "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
451
- "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
452
- "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
453
- "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
454
- "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
455
- "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
456
- "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
457
- "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
458
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
459
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
460
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
461
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
462
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
463
- "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
464
- "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
465
- "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
466
- "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
467
- "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
468
- "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
469
- "model.layers.40.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
470
- "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors",
471
- "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
472
- "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
473
- "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
474
- "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
475
- "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
476
- "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
477
- "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
478
- "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
479
- "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
480
- "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
481
- "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
482
- "model.layers.41.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
483
- "model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
484
- "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
485
- "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
486
- "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
487
- "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
488
- "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
489
- "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
490
- "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
491
- "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
492
- "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
493
- "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
494
- "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
495
- "model.layers.42.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
496
- "model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
497
- "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
498
- "model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
499
- "model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
500
- "model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
501
- "model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
502
- "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
503
- "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
504
- "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
505
- "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
506
- "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
507
- "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
508
- "model.layers.43.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
509
- "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
510
- "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
511
- "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
512
- "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
513
- "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
514
- "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
515
- "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
516
- "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
517
- "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
518
- "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
519
- "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
520
- "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
521
- "model.layers.44.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
522
- "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
523
- "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
524
- "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
525
- "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
526
- "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
527
- "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
528
- "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
529
- "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
530
- "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
531
- "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
532
- "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
533
- "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
534
- "model.layers.45.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
535
- "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
536
- "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
537
- "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
538
- "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
539
- "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
540
- "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
541
- "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
542
- "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
543
- "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
544
- "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
545
- "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
546
- "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
547
- "model.layers.46.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
548
- "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
549
- "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
550
- "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
551
- "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
552
- "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
553
- "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
554
- "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00007.safetensors",
555
- "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00007.safetensors",
556
- "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00007.safetensors",
557
- "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00007.safetensors",
558
- "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00007.safetensors",
559
- "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00007.safetensors",
560
- "model.layers.47.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
561
- "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors",
562
- "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
563
- "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
564
- "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
565
- "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
566
- "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
567
- "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
568
- "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
569
- "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
570
- "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
571
- "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
572
- "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
573
- "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
574
- "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
575
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
576
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
577
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
578
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
579
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
580
- "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
581
- "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
582
- "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
583
- "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
584
- "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
585
- "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
586
- "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
587
- "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
588
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
589
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
590
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
591
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
592
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
593
- "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
594
- "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
595
- "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
596
- "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
597
- "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
598
- "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
599
- "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
600
- "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
601
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
602
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
603
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
604
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
605
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
606
- "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
607
- "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
608
- "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
609
- "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
610
- "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
611
- "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
612
- "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
613
- "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
614
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
615
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
616
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
617
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
618
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
619
- "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
620
- "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
621
- "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
622
- "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
623
- "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
624
- "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
625
- "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
626
- "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
627
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
628
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
629
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
630
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
631
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
632
- "model.norm.weight": "model-00007-of-00007.safetensors"
633
  }
634
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 18419476480
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.norm.weight": "model-00004-of-00004.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
261
  }
262
  }
special_tokens_map.json CHANGED
@@ -1,20 +1,20 @@
1
  {
2
  "bos_token": {
3
- "content": "<|startoftext|>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|endoftext|>",
11
  "lstrip": false,
12
- "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|startoftext|>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<unk>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
- size 1033105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "add_bos_token": false,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
@@ -11,32 +11,36 @@
11
  "special": true
12
  },
13
  "1": {
14
- "content": "<|startoftext|>",
15
  "lstrip": false,
16
- "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
  "2": {
22
- "content": "<|endoftext|>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
28
  }
29
  },
30
- "bos_token": "<|startoftext|>",
31
  "clean_up_tokenization_spaces": false,
32
- "eos_token": "<|endoftext|>",
33
- "legacy": true,
34
- "max_length": null,
35
- "model_max_length": 4096,
36
- "pad_to_multiple_of": null,
37
- "pad_token": "<|startoftext|>",
38
- "pad_token_type_id": 0,
39
- "padding_side": "left",
40
  "sp_model_kwargs": {},
41
  "tokenizer_class": "LlamaTokenizer",
42
  "unk_token": "<unk>",
 
1
  {
2
+ "add_bos_token": true,
3
  "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
 
11
  "special": true
12
  },
13
  "1": {
14
+ "content": "<s>",
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
  "2": {
22
+ "content": "</s>",
23
  "lstrip": false,
24
+ "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
  }
37
  },
38
+ "bos_token": "<s>",
39
  "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<unk>",
 
 
 
 
44
  "sp_model_kwargs": {},
45
  "tokenizer_class": "LlamaTokenizer",
46
  "unk_token": "<unk>",