Add model files
Browse files- config.json +263 -0
- llm/added_tokens.json +7 -0
- llm/config.json +35 -0
- llm/config_slidingwindow.json +35 -0
- llm/generation_config.json +14 -0
- llm/merges.txt +0 -0
- llm/model-00001-of-00004.safetensors +3 -0
- llm/model-00002-of-00004.safetensors +3 -0
- llm/model-00003-of-00004.safetensors +3 -0
- llm/model-00004-of-00004.safetensors +3 -0
- llm/model.safetensors.index.json +346 -0
- llm/special_tokens_map.json +27 -0
- llm/tokenizer_config.json +61 -0
- llm/vocab.json +0 -0
- mm_projector/config.json +10 -0
- mm_projector/model.safetensors +3 -0
- vision_tower/config.json +19 -0
- vision_tower/model.safetensors +3 -0
- vision_tower/preprocessor_config.json +24 -0
config.json
ADDED
@@ -0,0 +1,263 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaLlamaModel"
|
5 |
+
],
|
6 |
+
"chat_template": null,
|
7 |
+
"drop_path_rate": 0.0,
|
8 |
+
"fps": 2.0,
|
9 |
+
"hidden_size": 3584,
|
10 |
+
"image_aspect_ratio": "resize",
|
11 |
+
"interpolate_mode": "linear",
|
12 |
+
"llm_cfg": {
|
13 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/llm",
|
14 |
+
"add_cross_attention": false,
|
15 |
+
"architectures": [
|
16 |
+
"Qwen2ForCausalLM"
|
17 |
+
],
|
18 |
+
"attention_dropout": 0.0,
|
19 |
+
"bad_words_ids": null,
|
20 |
+
"begin_suppress_tokens": null,
|
21 |
+
"bos_token_id": 151643,
|
22 |
+
"chunk_size_feed_forward": 0,
|
23 |
+
"cross_attention_hidden_size": null,
|
24 |
+
"decoder_start_token_id": null,
|
25 |
+
"diversity_penalty": 0.0,
|
26 |
+
"do_sample": false,
|
27 |
+
"early_stopping": false,
|
28 |
+
"encoder_no_repeat_ngram_size": 0,
|
29 |
+
"eos_token_id": 151645,
|
30 |
+
"exponential_decay_length_penalty": null,
|
31 |
+
"finetuning_task": null,
|
32 |
+
"forced_bos_token_id": null,
|
33 |
+
"forced_eos_token_id": null,
|
34 |
+
"hidden_act": "silu",
|
35 |
+
"hidden_size": 3584,
|
36 |
+
"id2label": {
|
37 |
+
"0": "LABEL_0",
|
38 |
+
"1": "LABEL_1"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 18944,
|
42 |
+
"is_decoder": false,
|
43 |
+
"is_encoder_decoder": false,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1
|
47 |
+
},
|
48 |
+
"length_penalty": 1.0,
|
49 |
+
"max_length": 20,
|
50 |
+
"max_position_embeddings": 1048576,
|
51 |
+
"max_window_layers": 28,
|
52 |
+
"min_length": 0,
|
53 |
+
"model_max_length": 1048576,
|
54 |
+
"model_type": "qwen2",
|
55 |
+
"no_repeat_ngram_size": 0,
|
56 |
+
"num_attention_heads": 28,
|
57 |
+
"num_beam_groups": 1,
|
58 |
+
"num_beams": 1,
|
59 |
+
"num_hidden_layers": 28,
|
60 |
+
"num_key_value_heads": 4,
|
61 |
+
"num_return_sequences": 1,
|
62 |
+
"output_attentions": false,
|
63 |
+
"output_hidden_states": false,
|
64 |
+
"output_scores": false,
|
65 |
+
"pad_token_id": null,
|
66 |
+
"prefix": null,
|
67 |
+
"problem_type": null,
|
68 |
+
"pruned_heads": {},
|
69 |
+
"remove_invalid_values": false,
|
70 |
+
"repetition_penalty": 1.0,
|
71 |
+
"return_dict": true,
|
72 |
+
"return_dict_in_generate": false,
|
73 |
+
"rms_norm_eps": 1e-06,
|
74 |
+
"rope_scaling": {
|
75 |
+
"factor": 4.0,
|
76 |
+
"type": "linear"
|
77 |
+
},
|
78 |
+
"rope_theta": 1062356830,
|
79 |
+
"sep_token_id": null,
|
80 |
+
"sliding_window": null,
|
81 |
+
"suppress_tokens": null,
|
82 |
+
"task_specific_params": null,
|
83 |
+
"temperature": 1.0,
|
84 |
+
"tf_legacy_loss": false,
|
85 |
+
"tie_encoder_decoder": false,
|
86 |
+
"tie_word_embeddings": false,
|
87 |
+
"tokenizer_class": null,
|
88 |
+
"tokenizer_model_max_length": 1048576,
|
89 |
+
"tokenizer_padding_side": "right",
|
90 |
+
"top_k": 50,
|
91 |
+
"top_p": 1.0,
|
92 |
+
"torch_dtype": "bfloat16",
|
93 |
+
"torchscript": false,
|
94 |
+
"typical_p": 1.0,
|
95 |
+
"use_bfloat16": false,
|
96 |
+
"use_cache": true,
|
97 |
+
"use_sliding_window": false,
|
98 |
+
"vocab_size": 151648
|
99 |
+
},
|
100 |
+
"mm_hidden_size": 1152,
|
101 |
+
"mm_projector_cfg": {
|
102 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/mm_projector",
|
103 |
+
"add_cross_attention": false,
|
104 |
+
"architectures": [
|
105 |
+
"MultimodalProjector"
|
106 |
+
],
|
107 |
+
"bad_words_ids": null,
|
108 |
+
"begin_suppress_tokens": null,
|
109 |
+
"bos_token_id": null,
|
110 |
+
"chunk_size_feed_forward": 0,
|
111 |
+
"cross_attention_hidden_size": null,
|
112 |
+
"decoder_start_token_id": null,
|
113 |
+
"diversity_penalty": 0.0,
|
114 |
+
"do_sample": false,
|
115 |
+
"early_stopping": false,
|
116 |
+
"encoder_no_repeat_ngram_size": 0,
|
117 |
+
"eos_token_id": null,
|
118 |
+
"exponential_decay_length_penalty": null,
|
119 |
+
"finetuning_task": null,
|
120 |
+
"forced_bos_token_id": null,
|
121 |
+
"forced_eos_token_id": null,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"is_decoder": false,
|
127 |
+
"is_encoder_decoder": false,
|
128 |
+
"label2id": {
|
129 |
+
"LABEL_0": 0,
|
130 |
+
"LABEL_1": 1
|
131 |
+
},
|
132 |
+
"length_penalty": 1.0,
|
133 |
+
"max_length": 20,
|
134 |
+
"min_length": 0,
|
135 |
+
"mm_projector_type": "mlp_downsample",
|
136 |
+
"model_type": "v2l_projector",
|
137 |
+
"no_repeat_ngram_size": 0,
|
138 |
+
"num_beam_groups": 1,
|
139 |
+
"num_beams": 1,
|
140 |
+
"num_return_sequences": 1,
|
141 |
+
"output_attentions": false,
|
142 |
+
"output_hidden_states": false,
|
143 |
+
"output_scores": false,
|
144 |
+
"pad_token_id": null,
|
145 |
+
"prefix": null,
|
146 |
+
"problem_type": null,
|
147 |
+
"pruned_heads": {},
|
148 |
+
"remove_invalid_values": false,
|
149 |
+
"repetition_penalty": 1.0,
|
150 |
+
"return_dict": true,
|
151 |
+
"return_dict_in_generate": false,
|
152 |
+
"sep_token_id": null,
|
153 |
+
"suppress_tokens": null,
|
154 |
+
"task_specific_params": null,
|
155 |
+
"temperature": 1.0,
|
156 |
+
"tf_legacy_loss": false,
|
157 |
+
"tie_encoder_decoder": false,
|
158 |
+
"tie_word_embeddings": true,
|
159 |
+
"tokenizer_class": null,
|
160 |
+
"top_k": 50,
|
161 |
+
"top_p": 1.0,
|
162 |
+
"torch_dtype": "bfloat16",
|
163 |
+
"torchscript": false,
|
164 |
+
"typical_p": 1.0,
|
165 |
+
"use_bfloat16": false
|
166 |
+
},
|
167 |
+
"mm_projector_lr": null,
|
168 |
+
"mm_use_im_patch_token": true,
|
169 |
+
"mm_use_im_start_end": false,
|
170 |
+
"mm_vision_select_feature": "cls_patch",
|
171 |
+
"mm_vision_select_layer": -2,
|
172 |
+
"model_dtype": "torch.bfloat16",
|
173 |
+
"model_type": "llava_llama",
|
174 |
+
"num_time_tokens": 0,
|
175 |
+
"num_video_frames": 2048,
|
176 |
+
"resume_path": "./output/qwen2-7b-longvila-1M",
|
177 |
+
"s2": false,
|
178 |
+
"s2_max_split_size": 336,
|
179 |
+
"s2_scales": "336,672,1008",
|
180 |
+
"soft_ce_std": 1.0,
|
181 |
+
"time_token_format": "<t{t}>",
|
182 |
+
"time_token_ids": [],
|
183 |
+
"transformers_version": "4.44.2",
|
184 |
+
"tune_language_model": true,
|
185 |
+
"tune_mm_projector": true,
|
186 |
+
"tune_vision_tower": true,
|
187 |
+
"vision_resolution": -1,
|
188 |
+
"vision_tower_cfg": {
|
189 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/vision_tower",
|
190 |
+
"add_cross_attention": false,
|
191 |
+
"architectures": [
|
192 |
+
"SiglipVisionModel"
|
193 |
+
],
|
194 |
+
"attention_dropout": 0.0,
|
195 |
+
"bad_words_ids": null,
|
196 |
+
"begin_suppress_tokens": null,
|
197 |
+
"bos_token_id": null,
|
198 |
+
"chunk_size_feed_forward": 0,
|
199 |
+
"cross_attention_hidden_size": null,
|
200 |
+
"decoder_start_token_id": null,
|
201 |
+
"diversity_penalty": 0.0,
|
202 |
+
"do_sample": false,
|
203 |
+
"early_stopping": false,
|
204 |
+
"encoder_no_repeat_ngram_size": 0,
|
205 |
+
"eos_token_id": null,
|
206 |
+
"exponential_decay_length_penalty": null,
|
207 |
+
"finetuning_task": null,
|
208 |
+
"forced_bos_token_id": null,
|
209 |
+
"forced_eos_token_id": null,
|
210 |
+
"hidden_act": "gelu_pytorch_tanh",
|
211 |
+
"hidden_size": 1152,
|
212 |
+
"id2label": {
|
213 |
+
"0": "LABEL_0",
|
214 |
+
"1": "LABEL_1"
|
215 |
+
},
|
216 |
+
"image_size": 384,
|
217 |
+
"intermediate_size": 4304,
|
218 |
+
"is_decoder": false,
|
219 |
+
"is_encoder_decoder": false,
|
220 |
+
"label2id": {
|
221 |
+
"LABEL_0": 0,
|
222 |
+
"LABEL_1": 1
|
223 |
+
},
|
224 |
+
"layer_norm_eps": 1e-06,
|
225 |
+
"length_penalty": 1.0,
|
226 |
+
"max_length": 20,
|
227 |
+
"min_length": 0,
|
228 |
+
"model_type": "siglip_vision_model",
|
229 |
+
"no_repeat_ngram_size": 0,
|
230 |
+
"num_attention_heads": 16,
|
231 |
+
"num_beam_groups": 1,
|
232 |
+
"num_beams": 1,
|
233 |
+
"num_channels": 3,
|
234 |
+
"num_hidden_layers": 27,
|
235 |
+
"num_return_sequences": 1,
|
236 |
+
"output_attentions": false,
|
237 |
+
"output_hidden_states": false,
|
238 |
+
"output_scores": false,
|
239 |
+
"pad_token_id": null,
|
240 |
+
"patch_size": 14,
|
241 |
+
"prefix": null,
|
242 |
+
"problem_type": null,
|
243 |
+
"pruned_heads": {},
|
244 |
+
"remove_invalid_values": false,
|
245 |
+
"repetition_penalty": 1.0,
|
246 |
+
"return_dict": true,
|
247 |
+
"return_dict_in_generate": false,
|
248 |
+
"sep_token_id": null,
|
249 |
+
"suppress_tokens": null,
|
250 |
+
"task_specific_params": null,
|
251 |
+
"temperature": 1.0,
|
252 |
+
"tf_legacy_loss": false,
|
253 |
+
"tie_encoder_decoder": false,
|
254 |
+
"tie_word_embeddings": true,
|
255 |
+
"tokenizer_class": null,
|
256 |
+
"top_k": 50,
|
257 |
+
"top_p": 1.0,
|
258 |
+
"torch_dtype": "bfloat16",
|
259 |
+
"torchscript": false,
|
260 |
+
"typical_p": 1.0,
|
261 |
+
"use_bfloat16": false
|
262 |
+
}
|
263 |
+
}
|
llm/added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644,
|
5 |
+
"[BOS]": 151647,
|
6 |
+
"[PAD]": 151646
|
7 |
+
}
|
llm/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/llm",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 1048576,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_max_length": 1048576,
|
16 |
+
"model_type": "qwen2",
|
17 |
+
"num_attention_heads": 28,
|
18 |
+
"num_hidden_layers": 28,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": {
|
22 |
+
"factor": 4.0,
|
23 |
+
"type": "linear"
|
24 |
+
},
|
25 |
+
"rope_theta": 1062356830,
|
26 |
+
"sliding_window": null,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_model_max_length": 1048576,
|
29 |
+
"tokenizer_padding_side": "right",
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.44.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"use_sliding_window": false,
|
34 |
+
"vocab_size": 151648
|
35 |
+
}
|
llm/config_slidingwindow.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output/qwen2-vl-7b-dynamic-sft-512k-2048frames-7nodes/llm",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 524288,
|
14 |
+
"max_window_layers": -1,
|
15 |
+
"model_max_length": 524288,
|
16 |
+
"model_type": "qwen2",
|
17 |
+
"num_attention_heads": 28,
|
18 |
+
"num_hidden_layers": 28,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": {
|
22 |
+
"factor": 4.0,
|
23 |
+
"type": "linear"
|
24 |
+
},
|
25 |
+
"rope_theta": 1062356830,
|
26 |
+
"sliding_window": 128,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"tokenizer_model_max_length": 524288,
|
29 |
+
"tokenizer_padding_side": "right",
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.44.2",
|
32 |
+
"use_cache": true,
|
33 |
+
"use_sliding_window": true,
|
34 |
+
"vocab_size": 151648
|
35 |
+
}
|
llm/generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.44.2"
|
14 |
+
}
|
llm/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
llm/model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8c3e121bc3545fb39ad5ef118954465432ae1459b2b3dd15a6dcc5aa7bee0d3
|
3 |
+
size 4874678888
|
llm/model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec7451832d8a655bd3c272c51c8f2de617d644efc8ef840723f7b244e13778e4
|
3 |
+
size 4932751008
|
llm/model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9764b061d5b29ad3b29f54136153b23166c1bdc1afa2a8d2517aa6d16ca1e2e8
|
3 |
+
size 4330865200
|
llm/model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56d76e373179374768c431e111e07816f7c2ef3fee3036728430f796f8abf0e
|
3 |
+
size 1087012992
|
llm/model.safetensors.index.json
ADDED
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 15225269248
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
92 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
104 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
116 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
212 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
224 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
248 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
344 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
345 |
+
}
|
346 |
+
}
|
llm/special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "[BOS]",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "[PAD]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
}
|
27 |
+
}
|
llm/tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "[PAD]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "[BOS]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"additional_special_tokens": [
|
46 |
+
"<|im_start|>",
|
47 |
+
"<|im_end|>"
|
48 |
+
],
|
49 |
+
"bos_token": "[BOS]",
|
50 |
+
"chat_template": "{% if messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n' }}{% endif %}{% for message in messages if message['content'] is not none %}{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
|
51 |
+
"clean_up_tokenization_spaces": false,
|
52 |
+
"eos_token": "<|im_end|>",
|
53 |
+
"errors": "replace",
|
54 |
+
"legacy": false,
|
55 |
+
"model_max_length": 524288,
|
56 |
+
"pad_token": "[PAD]",
|
57 |
+
"padding_side": "right",
|
58 |
+
"split_special_tokens": false,
|
59 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
60 |
+
"unk_token": null
|
61 |
+
}
|
llm/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mm_projector/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/mm_projector",
|
3 |
+
"architectures": [
|
4 |
+
"MultimodalProjector"
|
5 |
+
],
|
6 |
+
"mm_projector_type": "mlp_downsample",
|
7 |
+
"model_type": "v2l_projector",
|
8 |
+
"torch_dtype": "bfloat16",
|
9 |
+
"transformers_version": "4.44.2"
|
10 |
+
}
|
mm_projector/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccd96b8645deafa8f90a7235ef116e80958efa862db895bd62564ddcf8c27509
|
3 |
+
size 58753552
|
vision_tower/config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./output/qwen2-7b-longvila-1M/vision_tower",
|
3 |
+
"architectures": [
|
4 |
+
"SiglipVisionModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"hidden_act": "gelu_pytorch_tanh",
|
8 |
+
"hidden_size": 1152,
|
9 |
+
"image_size": 384,
|
10 |
+
"intermediate_size": 4304,
|
11 |
+
"layer_norm_eps": 1e-06,
|
12 |
+
"model_type": "siglip_vision_model",
|
13 |
+
"num_attention_heads": 16,
|
14 |
+
"num_channels": 3,
|
15 |
+
"num_hidden_layers": 27,
|
16 |
+
"patch_size": 14,
|
17 |
+
"torch_dtype": "bfloat16",
|
18 |
+
"transformers_version": "4.44.2"
|
19 |
+
}
|
vision_tower/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ac6e2946543c578bdba647bed37ad80cf6b99a5dac7d6933e95975001ff9ce
|
3 |
+
size 856506120
|
vision_tower/preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 3,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 384,
|
22 |
+
"width": 384
|
23 |
+
}
|
24 |
+
}
|