prakcoin commited on
Commit
ae7caa2
1 Parent(s): 468776c

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
  "_commit_hash": null,
3
- "_name_or_path": "./pretrained/InternVL2-8B",
4
  "architectures": [
5
  "InternVLChatModel"
6
  ],
@@ -96,105 +95,49 @@
96
  "top_p": 1.0,
97
  "torch_dtype": "bfloat16",
98
  "torchscript": false,
99
- "transformers_version": "4.44.2",
100
  "typical_p": 1.0,
101
  "use_bfloat16": true,
102
- "use_cache": false,
103
  "vocab_size": 92553
104
  },
105
- "max_dynamic_patch": 6,
106
  "min_dynamic_patch": 1,
107
  "model_type": "internvl_chat",
108
- "pad2square": false,
109
  "ps_version": "v2",
110
  "select_layer": -1,
111
  "template": "internlm2-chat",
112
  "torch_dtype": "bfloat16",
113
- "transformers_version": null,
114
  "use_backbone_lora": 0,
115
- "use_llm_lora": 16,
116
  "use_thumbnail": true,
117
  "vision_config": {
118
- "_name_or_path": "",
119
- "add_cross_attention": false,
120
  "architectures": [
121
  "InternVisionModel"
122
  ],
123
  "attention_dropout": 0.0,
124
- "bad_words_ids": null,
125
- "begin_suppress_tokens": null,
126
- "bos_token_id": null,
127
- "chunk_size_feed_forward": 0,
128
- "cross_attention_hidden_size": null,
129
- "decoder_start_token_id": null,
130
- "diversity_penalty": 0.0,
131
- "do_sample": false,
132
  "drop_path_rate": 0.0,
133
  "dropout": 0.0,
134
- "early_stopping": false,
135
- "encoder_no_repeat_ngram_size": 0,
136
- "eos_token_id": null,
137
- "exponential_decay_length_penalty": null,
138
- "finetuning_task": null,
139
- "forced_bos_token_id": null,
140
- "forced_eos_token_id": null,
141
  "hidden_act": "gelu",
142
  "hidden_size": 1024,
143
- "id2label": {
144
- "0": "LABEL_0",
145
- "1": "LABEL_1"
146
- },
147
  "image_size": 448,
148
  "initializer_factor": 1.0,
149
  "initializer_range": 0.02,
150
  "intermediate_size": 4096,
151
- "is_decoder": false,
152
- "is_encoder_decoder": false,
153
- "label2id": {
154
- "LABEL_0": 0,
155
- "LABEL_1": 1
156
- },
157
  "layer_norm_eps": 1e-06,
158
- "length_penalty": 1.0,
159
- "max_length": 20,
160
- "min_length": 0,
161
  "model_type": "intern_vit_6b",
162
- "no_repeat_ngram_size": 0,
163
  "norm_type": "layer_norm",
164
  "num_attention_heads": 16,
165
- "num_beam_groups": 1,
166
- "num_beams": 1,
167
  "num_channels": 3,
168
  "num_hidden_layers": 24,
169
- "num_return_sequences": 1,
170
  "output_attentions": false,
171
  "output_hidden_states": false,
172
- "output_scores": false,
173
- "pad_token_id": null,
174
  "patch_size": 14,
175
- "prefix": null,
176
- "problem_type": null,
177
- "pruned_heads": {},
178
  "qk_normalization": false,
179
  "qkv_bias": true,
180
- "remove_invalid_values": false,
181
- "repetition_penalty": 1.0,
182
  "return_dict": true,
183
- "return_dict_in_generate": false,
184
- "sep_token_id": null,
185
- "suppress_tokens": null,
186
- "task_specific_params": null,
187
- "temperature": 1.0,
188
- "tf_legacy_loss": false,
189
- "tie_encoder_decoder": false,
190
- "tie_word_embeddings": true,
191
- "tokenizer_class": null,
192
- "top_k": 50,
193
- "top_p": 1.0,
194
  "torch_dtype": "bfloat16",
195
- "torchscript": false,
196
- "transformers_version": "4.44.2",
197
- "typical_p": 1.0,
198
  "use_bfloat16": true,
199
  "use_flash_attn": true
200
  }
 
1
  {
2
  "_commit_hash": null,
 
3
  "architectures": [
4
  "InternVLChatModel"
5
  ],
 
95
  "top_p": 1.0,
96
  "torch_dtype": "bfloat16",
97
  "torchscript": false,
98
+ "transformers_version": "4.37.2",
99
  "typical_p": 1.0,
100
  "use_bfloat16": true,
101
+ "use_cache": true,
102
  "vocab_size": 92553
103
  },
104
+ "max_dynamic_patch": 12,
105
  "min_dynamic_patch": 1,
106
  "model_type": "internvl_chat",
 
107
  "ps_version": "v2",
108
  "select_layer": -1,
109
  "template": "internlm2-chat",
110
  "torch_dtype": "bfloat16",
 
111
  "use_backbone_lora": 0,
112
+ "use_llm_lora": 0,
113
  "use_thumbnail": true,
114
  "vision_config": {
 
 
115
  "architectures": [
116
  "InternVisionModel"
117
  ],
118
  "attention_dropout": 0.0,
 
 
 
 
 
 
 
 
119
  "drop_path_rate": 0.0,
120
  "dropout": 0.0,
 
 
 
 
 
 
 
121
  "hidden_act": "gelu",
122
  "hidden_size": 1024,
 
 
 
 
123
  "image_size": 448,
124
  "initializer_factor": 1.0,
125
  "initializer_range": 0.02,
126
  "intermediate_size": 4096,
 
 
 
 
 
 
127
  "layer_norm_eps": 1e-06,
 
 
 
128
  "model_type": "intern_vit_6b",
 
129
  "norm_type": "layer_norm",
130
  "num_attention_heads": 16,
 
 
131
  "num_channels": 3,
132
  "num_hidden_layers": 24,
 
133
  "output_attentions": false,
134
  "output_hidden_states": false,
 
 
135
  "patch_size": 14,
 
 
 
136
  "qk_normalization": false,
137
  "qkv_bias": true,
 
 
138
  "return_dict": true,
 
 
 
 
 
 
 
 
 
 
 
139
  "torch_dtype": "bfloat16",
140
+ "transformers_version": "4.37.2",
 
 
141
  "use_bfloat16": true,
142
  "use_flash_attn": true
143
  }
generation_config.json CHANGED
@@ -4,5 +4,5 @@
4
  92542,
5
  92543
6
  ],
7
- "transformers_version": "4.44.2"
8
  }
 
4
  92542,
5
  92543
6
  ],
7
+ "transformers_version": "4.37.2"
8
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d25bbb2d1997918a6f9baf0c648fa6d899bcb810a1c0e151f4a8d1ee46f3efa8
3
- size 4959423416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d112f20b1afd32d37f8d418e047e86a0c783a401b4cebc68148a154de617225
3
+ size 4939944336
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ddf1ada22fb21269f22df261bc143b089a62cc708f453717602f836ba1e927
3
- size 4942476624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2e5450569f9b71a29699dcac11c195df8bb088bb15bbc589b2f528a03292d0
3
+ size 4915914584
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6bbfc022ca9768d95246a33f2d45fb4b8a10831603052f5a13986a180e8c521
3
- size 4942476664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c241ab84d35a6c6d2cc457dd524435598da31bb466044d6314e7ad177b98d9
3
+ size 4915914592
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41bf312745b61b6b0df337ed72552c031bcff56ec000584f425a285879f72c86
3
- size 1381978232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c58295c7daf96c868634a759f79a911b08c5081cc6f3fc4082b2d8b1c8b225f
3
+ size 1379026920
model.safetensors.index.json CHANGED
@@ -1,555 +1,235 @@
1
  {
2
  "metadata": {
3
- "total_size": 16226228224
4
  },
5
  "weight_map": {
6
- "language_model.base_model.model.model.layers.0.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
7
- "language_model.base_model.model.model.layers.0.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
8
- "language_model.base_model.model.model.layers.0.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
9
- "language_model.base_model.model.model.layers.0.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
10
- "language_model.base_model.model.model.layers.0.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
11
- "language_model.base_model.model.model.layers.0.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
12
- "language_model.base_model.model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
13
- "language_model.base_model.model.model.layers.0.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
14
- "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
15
- "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
16
- "language_model.base_model.model.model.layers.0.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
17
- "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
18
- "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
19
- "language_model.base_model.model.model.layers.0.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
20
- "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
- "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
- "language_model.base_model.model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
23
- "language_model.base_model.model.model.layers.1.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
24
- "language_model.base_model.model.model.layers.1.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
25
- "language_model.base_model.model.model.layers.1.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
26
- "language_model.base_model.model.model.layers.1.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
27
- "language_model.base_model.model.model.layers.1.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
- "language_model.base_model.model.model.layers.1.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
- "language_model.base_model.model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
30
- "language_model.base_model.model.model.layers.1.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
31
- "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
32
- "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
33
- "language_model.base_model.model.model.layers.1.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
34
- "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
- "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
- "language_model.base_model.model.model.layers.1.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
37
- "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
- "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
- "language_model.base_model.model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
40
- "language_model.base_model.model.model.layers.10.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
41
- "language_model.base_model.model.model.layers.10.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
42
- "language_model.base_model.model.model.layers.10.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
43
- "language_model.base_model.model.model.layers.10.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
44
- "language_model.base_model.model.model.layers.10.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
45
- "language_model.base_model.model.model.layers.10.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
46
- "language_model.base_model.model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
47
- "language_model.base_model.model.model.layers.10.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
48
- "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
49
- "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
50
- "language_model.base_model.model.model.layers.10.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
51
- "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
52
- "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
53
- "language_model.base_model.model.model.layers.10.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
54
- "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
55
- "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
56
- "language_model.base_model.model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
57
- "language_model.base_model.model.model.layers.11.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
58
- "language_model.base_model.model.model.layers.11.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
59
- "language_model.base_model.model.model.layers.11.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
60
- "language_model.base_model.model.model.layers.11.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
61
- "language_model.base_model.model.model.layers.11.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
62
- "language_model.base_model.model.model.layers.11.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
63
- "language_model.base_model.model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
64
- "language_model.base_model.model.model.layers.11.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
65
- "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
- "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
- "language_model.base_model.model.model.layers.11.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
68
- "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
69
- "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
70
- "language_model.base_model.model.model.layers.11.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
71
- "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
72
- "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
73
- "language_model.base_model.model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
74
- "language_model.base_model.model.model.layers.12.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
75
- "language_model.base_model.model.model.layers.12.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
76
- "language_model.base_model.model.model.layers.12.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
77
- "language_model.base_model.model.model.layers.12.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
78
- "language_model.base_model.model.model.layers.12.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
79
- "language_model.base_model.model.model.layers.12.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
80
- "language_model.base_model.model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
81
- "language_model.base_model.model.model.layers.12.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
82
- "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
83
- "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
84
- "language_model.base_model.model.model.layers.12.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
85
- "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
86
- "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
87
- "language_model.base_model.model.model.layers.12.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
88
- "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
89
- "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
90
- "language_model.base_model.model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
91
- "language_model.base_model.model.model.layers.13.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
92
- "language_model.base_model.model.model.layers.13.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
93
- "language_model.base_model.model.model.layers.13.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
94
- "language_model.base_model.model.model.layers.13.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
95
- "language_model.base_model.model.model.layers.13.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
- "language_model.base_model.model.model.layers.13.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
- "language_model.base_model.model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
98
- "language_model.base_model.model.model.layers.13.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
99
- "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
100
- "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
101
- "language_model.base_model.model.model.layers.13.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
102
- "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
- "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
- "language_model.base_model.model.model.layers.13.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
105
- "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
- "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
- "language_model.base_model.model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
108
- "language_model.base_model.model.model.layers.14.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
109
- "language_model.base_model.model.model.layers.14.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
- "language_model.base_model.model.model.layers.14.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
- "language_model.base_model.model.model.layers.14.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
112
- "language_model.base_model.model.model.layers.14.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
- "language_model.base_model.model.model.layers.14.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
- "language_model.base_model.model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
115
- "language_model.base_model.model.model.layers.14.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
116
- "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
117
- "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
118
- "language_model.base_model.model.model.layers.14.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
119
- "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
120
- "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
121
- "language_model.base_model.model.model.layers.14.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
122
- "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
123
- "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
124
- "language_model.base_model.model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
125
- "language_model.base_model.model.model.layers.15.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
126
- "language_model.base_model.model.model.layers.15.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
127
- "language_model.base_model.model.model.layers.15.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
128
- "language_model.base_model.model.model.layers.15.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
129
- "language_model.base_model.model.model.layers.15.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
130
- "language_model.base_model.model.model.layers.15.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
131
- "language_model.base_model.model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
132
- "language_model.base_model.model.model.layers.15.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
133
- "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
134
- "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
135
- "language_model.base_model.model.model.layers.15.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
136
- "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
137
- "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
138
- "language_model.base_model.model.model.layers.15.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
139
- "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
140
- "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
141
- "language_model.base_model.model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
142
- "language_model.base_model.model.model.layers.16.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
143
- "language_model.base_model.model.model.layers.16.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
144
- "language_model.base_model.model.model.layers.16.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
145
- "language_model.base_model.model.model.layers.16.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
146
- "language_model.base_model.model.model.layers.16.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
147
- "language_model.base_model.model.model.layers.16.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
148
- "language_model.base_model.model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
149
- "language_model.base_model.model.model.layers.16.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
150
- "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
151
- "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
152
- "language_model.base_model.model.model.layers.16.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
153
- "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
154
- "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
155
- "language_model.base_model.model.model.layers.16.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
156
- "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
157
- "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
158
- "language_model.base_model.model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
159
- "language_model.base_model.model.model.layers.17.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
160
- "language_model.base_model.model.model.layers.17.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
161
- "language_model.base_model.model.model.layers.17.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
162
- "language_model.base_model.model.model.layers.17.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
163
- "language_model.base_model.model.model.layers.17.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
164
- "language_model.base_model.model.model.layers.17.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
165
- "language_model.base_model.model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
166
- "language_model.base_model.model.model.layers.17.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
167
- "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
168
- "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
169
- "language_model.base_model.model.model.layers.17.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
170
- "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
- "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
- "language_model.base_model.model.model.layers.17.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
173
- "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
- "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
- "language_model.base_model.model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
176
- "language_model.base_model.model.model.layers.18.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
177
- "language_model.base_model.model.model.layers.18.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
- "language_model.base_model.model.model.layers.18.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
- "language_model.base_model.model.model.layers.18.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
180
- "language_model.base_model.model.model.layers.18.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
- "language_model.base_model.model.model.layers.18.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
- "language_model.base_model.model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
183
- "language_model.base_model.model.model.layers.18.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
184
- "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
- "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
- "language_model.base_model.model.model.layers.18.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
187
- "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
- "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
- "language_model.base_model.model.model.layers.18.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
190
- "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
- "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
- "language_model.base_model.model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
193
- "language_model.base_model.model.model.layers.19.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
194
- "language_model.base_model.model.model.layers.19.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
195
- "language_model.base_model.model.model.layers.19.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
196
- "language_model.base_model.model.model.layers.19.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
197
- "language_model.base_model.model.model.layers.19.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
198
- "language_model.base_model.model.model.layers.19.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
199
- "language_model.base_model.model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
200
- "language_model.base_model.model.model.layers.19.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
201
- "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
202
- "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
203
- "language_model.base_model.model.model.layers.19.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
204
- "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
205
- "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
206
- "language_model.base_model.model.model.layers.19.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
207
- "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
208
- "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
209
- "language_model.base_model.model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
210
- "language_model.base_model.model.model.layers.2.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
211
- "language_model.base_model.model.model.layers.2.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
212
- "language_model.base_model.model.model.layers.2.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
213
- "language_model.base_model.model.model.layers.2.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
214
- "language_model.base_model.model.model.layers.2.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
215
- "language_model.base_model.model.model.layers.2.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
216
- "language_model.base_model.model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
217
- "language_model.base_model.model.model.layers.2.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
218
- "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
219
- "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
220
- "language_model.base_model.model.model.layers.2.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
221
- "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
222
- "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
223
- "language_model.base_model.model.model.layers.2.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
224
- "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
225
- "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
226
- "language_model.base_model.model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
227
- "language_model.base_model.model.model.layers.20.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
228
- "language_model.base_model.model.model.layers.20.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
229
- "language_model.base_model.model.model.layers.20.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
230
- "language_model.base_model.model.model.layers.20.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
231
- "language_model.base_model.model.model.layers.20.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
232
- "language_model.base_model.model.model.layers.20.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
233
- "language_model.base_model.model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
234
- "language_model.base_model.model.model.layers.20.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
235
- "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
236
- "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
237
- "language_model.base_model.model.model.layers.20.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
238
- "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
239
- "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
240
- "language_model.base_model.model.model.layers.20.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
241
- "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
242
- "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
243
- "language_model.base_model.model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
244
- "language_model.base_model.model.model.layers.21.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
245
- "language_model.base_model.model.model.layers.21.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
246
- "language_model.base_model.model.model.layers.21.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
247
- "language_model.base_model.model.model.layers.21.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
248
- "language_model.base_model.model.model.layers.21.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
249
- "language_model.base_model.model.model.layers.21.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
250
- "language_model.base_model.model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
251
- "language_model.base_model.model.model.layers.21.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
252
- "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
253
- "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
254
- "language_model.base_model.model.model.layers.21.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
255
- "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
256
- "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
257
- "language_model.base_model.model.model.layers.21.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
258
- "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
259
- "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
260
- "language_model.base_model.model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
261
- "language_model.base_model.model.model.layers.22.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
262
- "language_model.base_model.model.model.layers.22.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
263
- "language_model.base_model.model.model.layers.22.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
264
- "language_model.base_model.model.model.layers.22.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
265
- "language_model.base_model.model.model.layers.22.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
266
- "language_model.base_model.model.model.layers.22.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
267
- "language_model.base_model.model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
268
- "language_model.base_model.model.model.layers.22.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
269
- "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
270
- "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
271
- "language_model.base_model.model.model.layers.22.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
272
- "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
273
- "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
274
- "language_model.base_model.model.model.layers.22.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
275
- "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
276
- "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
277
- "language_model.base_model.model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
278
- "language_model.base_model.model.model.layers.23.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
279
- "language_model.base_model.model.model.layers.23.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
280
- "language_model.base_model.model.model.layers.23.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
281
- "language_model.base_model.model.model.layers.23.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
282
- "language_model.base_model.model.model.layers.23.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
283
- "language_model.base_model.model.model.layers.23.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
284
- "language_model.base_model.model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
285
- "language_model.base_model.model.model.layers.23.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
286
- "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
287
- "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
288
- "language_model.base_model.model.model.layers.23.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
289
- "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
290
- "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
291
- "language_model.base_model.model.model.layers.23.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
292
- "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
293
- "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
294
- "language_model.base_model.model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
295
- "language_model.base_model.model.model.layers.24.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
296
- "language_model.base_model.model.model.layers.24.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
297
- "language_model.base_model.model.model.layers.24.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
298
- "language_model.base_model.model.model.layers.24.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
299
- "language_model.base_model.model.model.layers.24.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
300
- "language_model.base_model.model.model.layers.24.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
301
- "language_model.base_model.model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
302
- "language_model.base_model.model.model.layers.24.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
303
- "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
304
- "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
305
- "language_model.base_model.model.model.layers.24.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
306
- "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
307
- "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
308
- "language_model.base_model.model.model.layers.24.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
309
- "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
310
- "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
311
- "language_model.base_model.model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
312
- "language_model.base_model.model.model.layers.25.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
313
- "language_model.base_model.model.model.layers.25.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
314
- "language_model.base_model.model.model.layers.25.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
315
- "language_model.base_model.model.model.layers.25.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
316
- "language_model.base_model.model.model.layers.25.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
317
- "language_model.base_model.model.model.layers.25.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
318
- "language_model.base_model.model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
319
- "language_model.base_model.model.model.layers.25.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
320
- "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
321
- "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
322
- "language_model.base_model.model.model.layers.25.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
323
- "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
324
- "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
325
- "language_model.base_model.model.model.layers.25.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
326
- "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
327
- "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
328
- "language_model.base_model.model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
329
- "language_model.base_model.model.model.layers.26.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
330
- "language_model.base_model.model.model.layers.26.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
331
- "language_model.base_model.model.model.layers.26.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
332
- "language_model.base_model.model.model.layers.26.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
333
- "language_model.base_model.model.model.layers.26.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
334
- "language_model.base_model.model.model.layers.26.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
335
- "language_model.base_model.model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
336
- "language_model.base_model.model.model.layers.26.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
337
- "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
338
- "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
339
- "language_model.base_model.model.model.layers.26.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
340
- "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
- "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
- "language_model.base_model.model.model.layers.26.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
343
- "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
344
- "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
345
- "language_model.base_model.model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
346
- "language_model.base_model.model.model.layers.27.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
347
- "language_model.base_model.model.model.layers.27.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
348
- "language_model.base_model.model.model.layers.27.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
349
- "language_model.base_model.model.model.layers.27.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
350
- "language_model.base_model.model.model.layers.27.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
351
- "language_model.base_model.model.model.layers.27.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
352
- "language_model.base_model.model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
353
- "language_model.base_model.model.model.layers.27.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
354
- "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
355
- "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
356
- "language_model.base_model.model.model.layers.27.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
357
- "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
358
- "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
359
- "language_model.base_model.model.model.layers.27.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
360
- "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
361
- "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
362
- "language_model.base_model.model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
363
- "language_model.base_model.model.model.layers.28.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
364
- "language_model.base_model.model.model.layers.28.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
365
- "language_model.base_model.model.model.layers.28.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
366
- "language_model.base_model.model.model.layers.28.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
367
- "language_model.base_model.model.model.layers.28.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
368
- "language_model.base_model.model.model.layers.28.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
369
- "language_model.base_model.model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
370
- "language_model.base_model.model.model.layers.28.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
371
- "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
372
- "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
373
- "language_model.base_model.model.model.layers.28.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
374
- "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
375
- "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
376
- "language_model.base_model.model.model.layers.28.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
377
- "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
- "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
- "language_model.base_model.model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
380
- "language_model.base_model.model.model.layers.29.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
381
- "language_model.base_model.model.model.layers.29.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
382
- "language_model.base_model.model.model.layers.29.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
383
- "language_model.base_model.model.model.layers.29.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
384
- "language_model.base_model.model.model.layers.29.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
- "language_model.base_model.model.model.layers.29.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
- "language_model.base_model.model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
387
- "language_model.base_model.model.model.layers.29.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
388
- "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
389
- "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
390
- "language_model.base_model.model.model.layers.29.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
391
- "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
392
- "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
393
- "language_model.base_model.model.model.layers.29.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
394
- "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
395
- "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
396
- "language_model.base_model.model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
397
- "language_model.base_model.model.model.layers.3.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
398
- "language_model.base_model.model.model.layers.3.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
399
- "language_model.base_model.model.model.layers.3.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
400
- "language_model.base_model.model.model.layers.3.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
401
- "language_model.base_model.model.model.layers.3.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
402
- "language_model.base_model.model.model.layers.3.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
403
- "language_model.base_model.model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
404
- "language_model.base_model.model.model.layers.3.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
405
- "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
406
- "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
407
- "language_model.base_model.model.model.layers.3.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
408
- "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
409
- "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
410
- "language_model.base_model.model.model.layers.3.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
411
- "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
412
- "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
413
- "language_model.base_model.model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
414
- "language_model.base_model.model.model.layers.30.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
415
- "language_model.base_model.model.model.layers.30.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
- "language_model.base_model.model.model.layers.30.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
- "language_model.base_model.model.model.layers.30.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
418
- "language_model.base_model.model.model.layers.30.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
419
- "language_model.base_model.model.model.layers.30.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
420
- "language_model.base_model.model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
421
- "language_model.base_model.model.model.layers.30.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
422
- "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
423
- "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
424
- "language_model.base_model.model.model.layers.30.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
425
- "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
426
- "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
427
- "language_model.base_model.model.model.layers.30.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
428
- "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
429
- "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
430
- "language_model.base_model.model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
431
- "language_model.base_model.model.model.layers.31.attention.wo.base_layer.weight": "model-00004-of-00004.safetensors",
432
- "language_model.base_model.model.model.layers.31.attention.wo.lora_A.default.weight": "model-00004-of-00004.safetensors",
433
- "language_model.base_model.model.model.layers.31.attention.wo.lora_B.default.weight": "model-00004-of-00004.safetensors",
434
- "language_model.base_model.model.model.layers.31.attention.wqkv.base_layer.weight": "model-00004-of-00004.safetensors",
435
- "language_model.base_model.model.model.layers.31.attention.wqkv.lora_A.default.weight": "model-00004-of-00004.safetensors",
436
- "language_model.base_model.model.model.layers.31.attention.wqkv.lora_B.default.weight": "model-00004-of-00004.safetensors",
437
- "language_model.base_model.model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
438
- "language_model.base_model.model.model.layers.31.feed_forward.w1.base_layer.weight": "model-00004-of-00004.safetensors",
439
- "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_A.default.weight": "model-00004-of-00004.safetensors",
440
- "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_B.default.weight": "model-00004-of-00004.safetensors",
441
- "language_model.base_model.model.model.layers.31.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
442
- "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
443
- "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
444
- "language_model.base_model.model.model.layers.31.feed_forward.w3.base_layer.weight": "model-00004-of-00004.safetensors",
445
- "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_A.default.weight": "model-00004-of-00004.safetensors",
446
- "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_B.default.weight": "model-00004-of-00004.safetensors",
447
- "language_model.base_model.model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
448
- "language_model.base_model.model.model.layers.4.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
449
- "language_model.base_model.model.model.layers.4.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
450
- "language_model.base_model.model.model.layers.4.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
451
- "language_model.base_model.model.model.layers.4.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
452
- "language_model.base_model.model.model.layers.4.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
453
- "language_model.base_model.model.model.layers.4.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
454
- "language_model.base_model.model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
455
- "language_model.base_model.model.model.layers.4.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
456
- "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
457
- "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
458
- "language_model.base_model.model.model.layers.4.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
459
- "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
460
- "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
461
- "language_model.base_model.model.model.layers.4.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
462
- "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
463
- "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
464
- "language_model.base_model.model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
465
- "language_model.base_model.model.model.layers.5.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
466
- "language_model.base_model.model.model.layers.5.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
467
- "language_model.base_model.model.model.layers.5.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
468
- "language_model.base_model.model.model.layers.5.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
469
- "language_model.base_model.model.model.layers.5.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
470
- "language_model.base_model.model.model.layers.5.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
471
- "language_model.base_model.model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
472
- "language_model.base_model.model.model.layers.5.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
473
- "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
474
- "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
475
- "language_model.base_model.model.model.layers.5.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
476
- "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
477
- "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
478
- "language_model.base_model.model.model.layers.5.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
479
- "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
480
- "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
481
- "language_model.base_model.model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
482
- "language_model.base_model.model.model.layers.6.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
483
- "language_model.base_model.model.model.layers.6.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
484
- "language_model.base_model.model.model.layers.6.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
485
- "language_model.base_model.model.model.layers.6.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
486
- "language_model.base_model.model.model.layers.6.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
487
- "language_model.base_model.model.model.layers.6.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
488
- "language_model.base_model.model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
489
- "language_model.base_model.model.model.layers.6.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
490
- "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
491
- "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
492
- "language_model.base_model.model.model.layers.6.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
493
- "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
494
- "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
495
- "language_model.base_model.model.model.layers.6.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
496
- "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
497
- "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
498
- "language_model.base_model.model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
499
- "language_model.base_model.model.model.layers.7.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
500
- "language_model.base_model.model.model.layers.7.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
501
- "language_model.base_model.model.model.layers.7.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
502
- "language_model.base_model.model.model.layers.7.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
503
- "language_model.base_model.model.model.layers.7.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
504
- "language_model.base_model.model.model.layers.7.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
505
- "language_model.base_model.model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
506
- "language_model.base_model.model.model.layers.7.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
507
- "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
508
- "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
509
- "language_model.base_model.model.model.layers.7.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
510
- "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
511
- "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
512
- "language_model.base_model.model.model.layers.7.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
513
- "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
514
- "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
515
- "language_model.base_model.model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
516
- "language_model.base_model.model.model.layers.8.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
517
- "language_model.base_model.model.model.layers.8.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
518
- "language_model.base_model.model.model.layers.8.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
519
- "language_model.base_model.model.model.layers.8.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
520
- "language_model.base_model.model.model.layers.8.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
521
- "language_model.base_model.model.model.layers.8.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
522
- "language_model.base_model.model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
523
- "language_model.base_model.model.model.layers.8.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
524
- "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
525
- "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
526
- "language_model.base_model.model.model.layers.8.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
527
- "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
528
- "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
529
- "language_model.base_model.model.model.layers.8.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
530
- "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
531
- "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
532
- "language_model.base_model.model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
533
- "language_model.base_model.model.model.layers.9.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
534
- "language_model.base_model.model.model.layers.9.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
535
- "language_model.base_model.model.model.layers.9.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
536
- "language_model.base_model.model.model.layers.9.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
537
- "language_model.base_model.model.model.layers.9.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
538
- "language_model.base_model.model.model.layers.9.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
539
- "language_model.base_model.model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
540
- "language_model.base_model.model.model.layers.9.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
541
- "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
542
- "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
543
- "language_model.base_model.model.model.layers.9.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
544
- "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
545
- "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
546
- "language_model.base_model.model.model.layers.9.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
547
- "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
548
- "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
549
- "language_model.base_model.model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
550
- "language_model.base_model.model.model.norm.weight": "model-00004-of-00004.safetensors",
551
- "language_model.base_model.model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
552
- "language_model.base_model.model.output.weight": "model-00004-of-00004.safetensors",
553
  "mlp1.0.bias": "model-00004-of-00004.safetensors",
554
  "mlp1.0.weight": "model-00004-of-00004.safetensors",
555
  "mlp1.1.bias": "model-00004-of-00004.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 16150730752
4
  },
5
  "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
  "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
  "mlp1.1.bias": "model-00004-of-00004.safetensors",