Hugging Face's logo

PCIResearch
/
TransCore-M

Text Generation
Transformers
PyTorch
English
transcorem
custom_code
Inference Endpoints
Model card Files Community
PCIResearch commited on
Commit
8496cd6
•
1 Parent(s): e1424b6

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +28 -12
  2. generation_config.json +8 -4
  3. pytorch_model-00001-of-00003.bin +2 -2
  4. pytorch_model-00002-of-00003.bin +2 -2
  5. pytorch_model-00003-of-00003.bin +2 -2
  6. pytorch_model.bin.index.json +327 -407
  7. qwen.tiktoken +0 -0
  8. special_tokens_map.json +3 -22
  9. tokenizer_config.json +11 -31
  10. trainer_state.json +0 -0
  11. training_args.bin +1 -1
config.json CHANGED
@@ -1,18 +1,26 @@
1
  {
2
  "_name_or_path": "TranscoreM",
3
  "architectures": [
4
- "TransCoreMLlamaForCausalLM"
5
  ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
 
 
 
 
 
 
 
8
  "freeze_mm_mlp_adapter": false,
9
- "hidden_act": "silu",
10
  "hidden_size": 5120,
11
  "image_aspect_ratio": "pad",
12
  "image_grid_pinpoints": null,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 13824,
15
- "max_position_embeddings": 4096,
 
 
16
  "mm_hidden_size": 1024,
17
  "mm_projector_lr": null,
18
  "mm_projector_type": "mlp2x_gelu",
@@ -22,21 +30,29 @@
22
  "mm_vision_select_layer": -2,
23
  "mm_vision_tower": "PCIResearch/clip-vit-large-patch14-336",
24
  "model_type": "transcorem",
 
25
  "num_attention_heads": 40,
26
  "num_hidden_layers": 40,
27
- "num_key_value_heads": 40,
28
- "pad_token_id": 0,
29
- "pretraining_tp": 1,
30
- "rms_norm_eps": 1e-06,
31
- "rope_scaling": null,
 
32
  "tie_word_embeddings": false,
 
33
  "torch_dtype": "bfloat16",
34
  "transformers_version": "4.31.0",
35
  "tune_entire_model": false,
36
  "tune_mm_mlp_adapter": false,
37
  "tune_vision_tower": false,
38
  "use_cache": true,
 
 
 
 
 
39
  "use_mm_proj": true,
40
  "vision_tower_lr": null,
41
- "vocab_size": 40076
42
  }
 
1
  {
2
  "_name_or_path": "TranscoreM",
3
  "architectures": [
4
+ "TransCoreMQWenForCausalLM"
5
  ],
6
+ "attn_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_qwen.QWenConfig",
9
+ "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
10
+ },
11
+ "bf16": false,
12
+ "emb_dropout_prob": 0.0,
13
+ "fp16": false,
14
+ "fp32": false,
15
  "freeze_mm_mlp_adapter": false,
 
16
  "hidden_size": 5120,
17
  "image_aspect_ratio": "pad",
18
  "image_grid_pinpoints": null,
19
  "initializer_range": 0.02,
20
+ "intermediate_size": 27392,
21
+ "kv_channels": 128,
22
+ "layer_norm_epsilon": 1e-06,
23
+ "max_position_embeddings": 8192,
24
  "mm_hidden_size": 1024,
25
  "mm_projector_lr": null,
26
  "mm_projector_type": "mlp2x_gelu",
 
30
  "mm_vision_select_layer": -2,
31
  "mm_vision_tower": "PCIResearch/clip-vit-large-patch14-336",
32
  "model_type": "transcorem",
33
+ "no_bias": true,
34
  "num_attention_heads": 40,
35
  "num_hidden_layers": 40,
36
+ "onnx_safe": null,
37
+ "rotary_emb_base": 10000,
38
+ "rotary_pct": 1.0,
39
+ "scale_attn_weights": true,
40
+ "seq_length": 2048,
41
+ "softmax_in_fp32": false,
42
  "tie_word_embeddings": false,
43
+ "tokenizer_class": "QWenTokenizer",
44
  "torch_dtype": "bfloat16",
45
  "transformers_version": "4.31.0",
46
  "tune_entire_model": false,
47
  "tune_mm_mlp_adapter": false,
48
  "tune_vision_tower": false,
49
  "use_cache": true,
50
+ "use_cache_kernel": false,
51
+ "use_cache_quantization": false,
52
+ "use_dynamic_ntk": true,
53
+ "use_flash_attn": "auto",
54
+ "use_logn_attn": true,
55
  "use_mm_proj": true,
56
  "vision_tower_lr": null,
57
+ "vocab_size": 152064
58
  }
generation_config.json CHANGED
@@ -1,7 +1,11 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
 
 
 
 
6
  "transformers_version": "4.31.0"
7
  }
 
1
  {
2
+ "chat_format": "chatml",
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 512,
6
+ "max_window_size": 6144,
7
+ "pad_token_id": 151643,
8
+ "top_k": 0,
9
+ "top_p": 0.5,
10
  "transformers_version": "4.31.0"
11
  }
pytorch_model-00001-of-00003.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de02cbbc48e89b149e1f62c021d493334e182df83bf25088cb4a83233d78eddb
3
- size 9978995635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d26e6bdb05f2a63b3f57771b1d12dc2eb46d87ef1c5ef7acad6a2503682c59
3
+ size 9963536445
pytorch_model-00002-of-00003.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1feffa38d5faaec608395a5c26c8922e87dada3f4f60f6c0cf1e9b816bf1e870
3
- size 9956592151
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a334d3fc0e4d08f5f421e086e67dd1e290ea8aaa9f9dbf2087c23f6047e514
3
+ size 9878405831
pytorch_model-00003-of-00003.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:477fa092a4777ee58e25ae12a4a8020532bf40b3e082e9895a7280893e21ebad
3
- size 6324617089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8912e2567776930ec3d1c7f534340f639432c6705c43b738353a35335fc972a6
3
+ size 8555684085
pytorch_model.bin.index.json CHANGED
@@ -1,414 +1,334 @@
1
  {
2
  "metadata": {
3
- "total_size": 26260065280
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
- "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
- "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
- "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
- "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
- "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
- "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
- "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
- "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
- "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
- "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
- "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
252
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
- "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
- "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
- "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
- "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
- "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
- "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
- "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
- "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
- "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
- "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
- "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
- "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
- "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
- "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
- "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
- "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
- "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
- "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
- "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
- "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
- "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
- "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
- "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
- "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
- "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
- "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
- "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
- "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
- "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
- "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
- "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
- "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
- "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
- "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
- "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
- "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
- "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
- "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
- "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
- "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
- "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
- "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
- "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
- "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
- "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
- "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
- "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
- "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
- "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
- "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
- "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
- "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
- "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
- "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
- "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
- "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
- "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
- "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
- "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
- "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
- "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
- "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
- "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
- "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
- "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
- "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
- "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
- "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
- "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
- "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
- "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
- "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
- "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
- "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
- "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
- "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
- "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
- "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
- "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
- "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
350
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
351
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
352
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
353
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
354
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
355
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
356
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
357
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
358
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
363
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
- "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
409
- "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
410
- "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
411
- "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
412
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
413
  }
414
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 28397516800
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
8
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
9
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.h.0.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.h.0.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.h.1.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.h.1.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
27
+ "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00003.bin",
28
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.h.10.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.h.10.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
31
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
32
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
33
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
35
+ "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00003.bin",
36
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "transformer.h.11.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
38
+ "transformer.h.11.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
39
+ "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
40
+ "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
41
+ "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00003.bin",
43
+ "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00003.bin",
44
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "transformer.h.12.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
46
+ "transformer.h.12.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
47
+ "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
48
+ "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
49
+ "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00003.bin",
51
+ "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00003.bin",
52
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.h.13.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.h.13.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.h.14.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.h.14.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.h.15.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.h.15.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.h.16.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.h.16.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
79
+ "transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
80
+ "transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
81
+ "transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
83
+ "transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00003.bin",
84
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.h.17.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.h.17.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.h.18.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.h.18.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.h.19.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.h.19.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
104
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
105
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
106
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
107
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00003.bin",
108
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
109
+ "transformer.h.2.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
110
+ "transformer.h.2.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
111
+ "transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
112
+ "transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
113
+ "transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
115
+ "transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00003.bin",
116
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
117
+ "transformer.h.20.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
118
+ "transformer.h.20.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
119
+ "transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
120
+ "transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
121
+ "transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
123
+ "transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00003.bin",
124
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "transformer.h.21.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
126
+ "transformer.h.21.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
127
+ "transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
128
+ "transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
129
+ "transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
130
+ "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
131
+ "transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00003.bin",
132
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "transformer.h.22.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
134
+ "transformer.h.22.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
135
+ "transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
136
+ "transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
137
+ "transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
139
+ "transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00003.bin",
140
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "transformer.h.23.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
142
+ "transformer.h.23.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
143
+ "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
144
+ "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
145
+ "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00003.bin",
147
+ "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00003.bin",
148
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "transformer.h.24.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
150
+ "transformer.h.24.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
151
+ "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
152
+ "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
153
+ "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00003.bin",
155
+ "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00003.bin",
156
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
157
+ "transformer.h.25.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
158
+ "transformer.h.25.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
159
+ "transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
160
+ "transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
161
+ "transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00003.bin",
163
+ "transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00003.bin",
164
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "transformer.h.26.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
166
+ "transformer.h.26.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
167
+ "transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
168
+ "transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
169
+ "transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00003.bin",
171
+ "transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00003.bin",
172
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
173
+ "transformer.h.27.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
174
+ "transformer.h.27.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
175
+ "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
176
+ "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
177
+ "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00003.bin",
179
+ "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00003.bin",
180
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "transformer.h.28.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
182
+ "transformer.h.28.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
183
+ "transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
184
+ "transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
185
+ "transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00003.bin",
187
+ "transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00003.bin",
188
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
189
+ "transformer.h.29.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
190
+ "transformer.h.29.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
191
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
192
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
193
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
194
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
195
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00003.bin",
196
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
197
+ "transformer.h.3.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
198
+ "transformer.h.3.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
199
+ "transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
200
+ "transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
201
+ "transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00003.bin",
203
+ "transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00003.bin",
204
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "transformer.h.30.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
206
+ "transformer.h.30.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
207
+ "transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
208
+ "transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
209
+ "transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00003.bin",
211
+ "transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00003.bin",
212
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
213
+ "transformer.h.31.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
214
+ "transformer.h.31.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
215
+ "transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
216
+ "transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
217
+ "transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00003.bin",
219
+ "transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00003.bin",
220
+ "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
221
+ "transformer.h.32.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
222
+ "transformer.h.32.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
223
+ "transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
224
+ "transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
225
+ "transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00003.bin",
227
+ "transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00003.bin",
228
+ "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
229
+ "transformer.h.33.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
230
+ "transformer.h.33.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
231
+ "transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
232
+ "transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
233
+ "transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
234
+ "transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00003.bin",
235
+ "transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00003.bin",
236
+ "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "transformer.h.34.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
238
+ "transformer.h.34.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
239
+ "transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
240
+ "transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
241
+ "transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00003.bin",
243
+ "transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00003.bin",
244
+ "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
245
+ "transformer.h.35.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
246
+ "transformer.h.35.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
247
+ "transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
248
+ "transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
249
+ "transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00003.bin",
251
+ "transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00003.bin",
252
+ "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
253
+ "transformer.h.36.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
254
+ "transformer.h.36.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
255
+ "transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
256
+ "transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
257
+ "transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00003.bin",
259
+ "transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00003.bin",
260
+ "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "transformer.h.37.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
262
+ "transformer.h.37.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
263
+ "transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
264
+ "transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
265
+ "transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00003.bin",
267
+ "transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00003.bin",
268
+ "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
269
+ "transformer.h.38.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
270
+ "transformer.h.38.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
271
+ "transformer.h.39.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
272
+ "transformer.h.39.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
273
+ "transformer.h.39.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
274
+ "transformer.h.39.ln_1.weight": "pytorch_model-00003-of-00003.bin",
275
+ "transformer.h.39.ln_2.weight": "pytorch_model-00003-of-00003.bin",
276
+ "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
277
+ "transformer.h.39.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
278
+ "transformer.h.39.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
279
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
280
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
281
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
283
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00003.bin",
284
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "transformer.h.4.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
286
+ "transformer.h.4.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
287
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
288
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
289
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
291
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00003.bin",
292
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "transformer.h.5.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
294
+ "transformer.h.5.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
295
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
296
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
297
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
299
+ "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00003.bin",
300
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "transformer.h.6.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
302
+ "transformer.h.6.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
303
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
304
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
305
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
306
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
307
+ "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00003.bin",
308
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
309
+ "transformer.h.7.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
310
+ "transformer.h.7.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
311
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
312
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
313
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
315
+ "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00003.bin",
316
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
317
+ "transformer.h.8.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
318
+ "transformer.h.8.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
319
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
320
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
321
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
323
+ "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00003.bin",
324
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "transformer.h.9.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
326
+ "transformer.h.9.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
327
+ "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
328
+ "transformer.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
329
+ "transformer.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
330
+ "transformer.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
331
+ "transformer.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
332
+ "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
333
  }
334
  }
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,24 +1,5 @@
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": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "bos_token": "<|im_start|>",
3
+ "eos_token": "<|im_end|>",
4
+ "pad_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer_config.json CHANGED
@@ -1,36 +1,16 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
  },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": true,
22
  "model_max_length": 2048,
23
- "pad_token": null,
24
  "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false
34
- },
35
- "use_fast": true
36
  }
 
1
  {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_qwen.QWenTokenizer",
5
+ null
6
+ ]
 
 
 
 
7
  },
8
+ "bos_token": "<|im_start|>",
9
+ "clean_up_tokenization_spaces": true,
10
+ "eos_token": "<|im_end|>",
 
 
 
 
 
 
 
11
  "model_max_length": 2048,
12
+ "pad_token": "<|endoftext|>",
13
  "padding_side": "right",
14
+ "tokenizer_class": "QWenTokenizer",
15
+ "use_fast": false
 
 
 
 
 
 
 
 
 
16
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d0e6b0bde37a458a6ed069e0ae44ee7c96a376d4fd79093e2cb4b5c393918aa
3
  size 6139
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b180ca7b1e5234bc38c8afe17d9cd88753628f5ba99e8ed5b0b3d694bd8924
3
  size 6139