Delete llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500
Browse files- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/added_tokens.json +0 -6
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/config.json +0 -221
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/generation_config.json +0 -14
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/latest +0 -1
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/merges.txt +0 -0
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00001-of-00004.safetensors +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00002-of-00004.safetensors +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00003-of-00004.safetensors +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00004-of-00004.safetensors +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model.safetensors.index.json +0 -772
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_0.pth +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_1.pth +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_2.pth +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_3.pth +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/scheduler.pt +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/special_tokens_map.json +0 -20
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/tokenizer.json +0 -0
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/tokenizer_config.json +0 -53
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/trainer_state.json +0 -0
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/training_args.bin +0 -3
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/vocab.json +0 -0
- llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/zero_to_fp32.py +0 -604
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/added_tokens.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<image>": 151646,
|
| 3 |
-
"<|endoftext|>": 151643,
|
| 4 |
-
"<|im_end|>": 151645,
|
| 5 |
-
"<|im_start|>": 151644
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/config.json
DELETED
|
@@ -1,221 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-si",
|
| 3 |
-
"add_faster_video": false,
|
| 4 |
-
"add_time_instruction": true,
|
| 5 |
-
"architectures": [
|
| 6 |
-
"LlavaQwenForCausalLM"
|
| 7 |
-
],
|
| 8 |
-
"attention_dropout": 0.0,
|
| 9 |
-
"bos_token_id": 151643,
|
| 10 |
-
"eos_token_id": 151645,
|
| 11 |
-
"faster_token_stride": 10,
|
| 12 |
-
"force_sample": true,
|
| 13 |
-
"hidden_act": "silu",
|
| 14 |
-
"hidden_size": 3584,
|
| 15 |
-
"ignore_index": -100,
|
| 16 |
-
"image_aspect_ratio": "anyres_max_9",
|
| 17 |
-
"image_crop_resolution": null,
|
| 18 |
-
"image_grid_pinpoints": [
|
| 19 |
-
[
|
| 20 |
-
384,
|
| 21 |
-
384
|
| 22 |
-
],
|
| 23 |
-
[
|
| 24 |
-
384,
|
| 25 |
-
768
|
| 26 |
-
],
|
| 27 |
-
[
|
| 28 |
-
384,
|
| 29 |
-
1152
|
| 30 |
-
],
|
| 31 |
-
[
|
| 32 |
-
384,
|
| 33 |
-
1536
|
| 34 |
-
],
|
| 35 |
-
[
|
| 36 |
-
384,
|
| 37 |
-
1920
|
| 38 |
-
],
|
| 39 |
-
[
|
| 40 |
-
384,
|
| 41 |
-
2304
|
| 42 |
-
],
|
| 43 |
-
[
|
| 44 |
-
768,
|
| 45 |
-
384
|
| 46 |
-
],
|
| 47 |
-
[
|
| 48 |
-
768,
|
| 49 |
-
768
|
| 50 |
-
],
|
| 51 |
-
[
|
| 52 |
-
768,
|
| 53 |
-
1152
|
| 54 |
-
],
|
| 55 |
-
[
|
| 56 |
-
768,
|
| 57 |
-
1536
|
| 58 |
-
],
|
| 59 |
-
[
|
| 60 |
-
768,
|
| 61 |
-
1920
|
| 62 |
-
],
|
| 63 |
-
[
|
| 64 |
-
768,
|
| 65 |
-
2304
|
| 66 |
-
],
|
| 67 |
-
[
|
| 68 |
-
1152,
|
| 69 |
-
384
|
| 70 |
-
],
|
| 71 |
-
[
|
| 72 |
-
1152,
|
| 73 |
-
768
|
| 74 |
-
],
|
| 75 |
-
[
|
| 76 |
-
1152,
|
| 77 |
-
1152
|
| 78 |
-
],
|
| 79 |
-
[
|
| 80 |
-
1152,
|
| 81 |
-
1536
|
| 82 |
-
],
|
| 83 |
-
[
|
| 84 |
-
1152,
|
| 85 |
-
1920
|
| 86 |
-
],
|
| 87 |
-
[
|
| 88 |
-
1152,
|
| 89 |
-
2304
|
| 90 |
-
],
|
| 91 |
-
[
|
| 92 |
-
1536,
|
| 93 |
-
384
|
| 94 |
-
],
|
| 95 |
-
[
|
| 96 |
-
1536,
|
| 97 |
-
768
|
| 98 |
-
],
|
| 99 |
-
[
|
| 100 |
-
1536,
|
| 101 |
-
1152
|
| 102 |
-
],
|
| 103 |
-
[
|
| 104 |
-
1536,
|
| 105 |
-
1536
|
| 106 |
-
],
|
| 107 |
-
[
|
| 108 |
-
1536,
|
| 109 |
-
1920
|
| 110 |
-
],
|
| 111 |
-
[
|
| 112 |
-
1536,
|
| 113 |
-
2304
|
| 114 |
-
],
|
| 115 |
-
[
|
| 116 |
-
1920,
|
| 117 |
-
384
|
| 118 |
-
],
|
| 119 |
-
[
|
| 120 |
-
1920,
|
| 121 |
-
768
|
| 122 |
-
],
|
| 123 |
-
[
|
| 124 |
-
1920,
|
| 125 |
-
1152
|
| 126 |
-
],
|
| 127 |
-
[
|
| 128 |
-
1920,
|
| 129 |
-
1536
|
| 130 |
-
],
|
| 131 |
-
[
|
| 132 |
-
1920,
|
| 133 |
-
1920
|
| 134 |
-
],
|
| 135 |
-
[
|
| 136 |
-
1920,
|
| 137 |
-
2304
|
| 138 |
-
],
|
| 139 |
-
[
|
| 140 |
-
2304,
|
| 141 |
-
384
|
| 142 |
-
],
|
| 143 |
-
[
|
| 144 |
-
2304,
|
| 145 |
-
768
|
| 146 |
-
],
|
| 147 |
-
[
|
| 148 |
-
2304,
|
| 149 |
-
1152
|
| 150 |
-
],
|
| 151 |
-
[
|
| 152 |
-
2304,
|
| 153 |
-
1536
|
| 154 |
-
],
|
| 155 |
-
[
|
| 156 |
-
2304,
|
| 157 |
-
1920
|
| 158 |
-
],
|
| 159 |
-
[
|
| 160 |
-
2304,
|
| 161 |
-
2304
|
| 162 |
-
]
|
| 163 |
-
],
|
| 164 |
-
"image_split_resolution": null,
|
| 165 |
-
"image_token_index": 151646,
|
| 166 |
-
"initializer_range": 0.02,
|
| 167 |
-
"intermediate_size": 18944,
|
| 168 |
-
"max_position_embeddings": 32768,
|
| 169 |
-
"max_window_layers": 28,
|
| 170 |
-
"mm_hidden_size": 1152,
|
| 171 |
-
"mm_newline_position": "grid",
|
| 172 |
-
"mm_patch_merge_type": "spatial_unpad",
|
| 173 |
-
"mm_projector_lr": null,
|
| 174 |
-
"mm_projector_type": "mlp2x_gelu",
|
| 175 |
-
"mm_resampler_type": null,
|
| 176 |
-
"mm_spatial_pool_mode": "bilinear",
|
| 177 |
-
"mm_spatial_pool_stride": 2,
|
| 178 |
-
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 179 |
-
"mm_use_im_patch_token": false,
|
| 180 |
-
"mm_use_im_start_end": false,
|
| 181 |
-
"mm_vision_select_feature": "patch",
|
| 182 |
-
"mm_vision_select_layer": -2,
|
| 183 |
-
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
| 184 |
-
"mm_vision_tower_lr": 2e-06,
|
| 185 |
-
"model_type": "llava",
|
| 186 |
-
"num_attention_heads": 28,
|
| 187 |
-
"num_hidden_layers": 28,
|
| 188 |
-
"num_key_value_heads": 4,
|
| 189 |
-
"pos_skipping_range": 4096,
|
| 190 |
-
"projector_hidden_act": "gelu",
|
| 191 |
-
"rms_norm_eps": 1e-06,
|
| 192 |
-
"rope_scaling": null,
|
| 193 |
-
"rope_theta": 1000000.0,
|
| 194 |
-
"sliding_window": 131072,
|
| 195 |
-
"text_config": {
|
| 196 |
-
"model_type": "llama"
|
| 197 |
-
},
|
| 198 |
-
"tie_word_embeddings": false,
|
| 199 |
-
"tokenizer_model_max_length": 32768,
|
| 200 |
-
"tokenizer_padding_side": "right",
|
| 201 |
-
"torch_dtype": "bfloat16",
|
| 202 |
-
"transformers_version": "4.40.0.dev0",
|
| 203 |
-
"use_cache": false,
|
| 204 |
-
"use_mm_proj": true,
|
| 205 |
-
"use_pos_skipping": false,
|
| 206 |
-
"use_sliding_window": false,
|
| 207 |
-
"vision_config": {
|
| 208 |
-
"hidden_size": 1024,
|
| 209 |
-
"image_size": 336,
|
| 210 |
-
"intermediate_size": 4096,
|
| 211 |
-
"model_type": "clip_vision_model",
|
| 212 |
-
"num_attention_heads": 16,
|
| 213 |
-
"num_hidden_layers": 24,
|
| 214 |
-
"patch_size": 14,
|
| 215 |
-
"projection_dim": 768,
|
| 216 |
-
"vocab_size": 32000
|
| 217 |
-
},
|
| 218 |
-
"vision_feature_layer": -2,
|
| 219 |
-
"vision_feature_select_strategy": "default",
|
| 220 |
-
"vision_tower_pretrained": null
|
| 221 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/generation_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 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": "4.40.0.dev0"
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b907087c7236211452b84f8f9ca6df03f45a1c369c24429251cd2a9a6301b614
|
| 3 |
-
size 24091055846
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:78abb3c04264b99dbfc7b9f7819204fe8800d794700fbd2a23fa555c9490f4d4
|
| 3 |
-
size 24091055846
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9a94007ad2a45f7522e98edf4cd7bba88fa40fb6ccc06534b57979adf4c2b439
|
| 3 |
-
size 24091055846
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f2d10a9a24e07b23935a919c3be6f835de7b2f4509e644c902b12e55d27f395f
|
| 3 |
-
size 24091055846
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_0_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6cb78c87ca325d6c30238b1c10790ac9525efd0975ddab01716cf4b96527a33b
|
| 3 |
-
size 419351
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_1_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b604565d7ef735dcd1fe53e6cd337f405c0bbab98a65139ec42577be32317a87
|
| 3 |
-
size 419351
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_2_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c0228ec2cdc819fb46fa1207ae123b82ecf9917633c82511bc0e9407bc5f5e01
|
| 3 |
-
size 419351
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/global_step2500/zero_pp_rank_3_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:62f7afd84fdcc79738e191fc4676ed0ec24fb5ac2c3e1bfd49e08010ebedc1a2
|
| 3 |
-
size 419351
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/latest
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
global_step2500
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00001-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d0227c664d147589418ecc33161e885422be38a6314bb2a2bcb2b4cf05f0b23c
|
| 3 |
-
size 4877668032
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00002-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b190799bc2500e485b11fb2edf2834498adb50c400a9f4345e8eea6b4a047ae8
|
| 3 |
-
size 4932751008
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00003-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9d87e0bd652ce2b77650161a556282c02fc6fe9d6fe4306e238b398d9c84bc14
|
| 3 |
-
size 4994571904
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model-00004-of-00004.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:280869c7cec87417a1312d300b9c8e37dd2973cb0ac1a86f105d3cf3955fce27
|
| 3 |
-
size 1255812224
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/model.safetensors.index.json
DELETED
|
@@ -1,772 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_size": 16060697664
|
| 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.image_newline": "model-00001-of-00004.safetensors",
|
| 9 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
-
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
-
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
-
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
-
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
-
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
-
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
-
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
-
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
-
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
-
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
-
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
-
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
-
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
-
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
-
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
-
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
-
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
-
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
-
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
-
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
-
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
-
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
-
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
-
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
-
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
-
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
-
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
-
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
-
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
-
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
-
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
-
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
-
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
-
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
-
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
-
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
-
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
-
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
-
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
-
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
-
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
-
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
-
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
-
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
-
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
-
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
-
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
-
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
-
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
-
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
-
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
-
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
-
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
-
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
-
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
-
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
-
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
-
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
-
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
-
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
-
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
-
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
-
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
-
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
-
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
-
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
-
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
-
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
-
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
-
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
-
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
-
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
-
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
-
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
-
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
-
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
-
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
-
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
-
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
-
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
-
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
-
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
-
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
-
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
-
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
-
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
-
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
-
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
-
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
-
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
-
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
-
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
-
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
-
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
-
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
-
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
-
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
-
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
-
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
-
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
-
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
-
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
-
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
-
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
-
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
-
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
-
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
-
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
-
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
-
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
-
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
-
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
-
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
-
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
-
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
-
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
-
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
-
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
-
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
-
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
-
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
-
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
-
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
-
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
-
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
-
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
-
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
-
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
-
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
-
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
-
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
-
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
-
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
-
"model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
|
| 346 |
-
"model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
|
| 347 |
-
"model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
|
| 348 |
-
"model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
|
| 349 |
-
"model.norm.weight": "model-00003-of-00004.safetensors",
|
| 350 |
-
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
|
| 351 |
-
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
|
| 352 |
-
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
|
| 353 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 354 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 355 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 356 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 357 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 358 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 359 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 360 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 361 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 362 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 364 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 366 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 367 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 368 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 369 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 370 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 371 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 372 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 373 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 374 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 375 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 376 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 377 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 378 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 379 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 380 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 381 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 382 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 384 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 385 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 386 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 387 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 388 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 389 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 390 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 391 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 392 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 393 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 394 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 395 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 396 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 398 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 399 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 400 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 401 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 402 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 403 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 404 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 405 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 406 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 407 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 408 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 409 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 410 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 411 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 412 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 413 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 414 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 415 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 416 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 417 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 418 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 419 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 420 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 421 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 422 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 423 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 424 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 425 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 426 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 427 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 428 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 429 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 430 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 431 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 432 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 433 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 434 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 435 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 436 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 437 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 438 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 439 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 440 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 441 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 442 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 443 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 444 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 445 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 446 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 447 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 448 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 449 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 450 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 451 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 452 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 453 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 454 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 455 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 456 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 457 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 458 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 459 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 460 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 461 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 462 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 463 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 464 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 465 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 466 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 467 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 468 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 469 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 470 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 471 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 472 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 473 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 474 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 475 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 476 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 477 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 478 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 479 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 480 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 481 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 482 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 483 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 484 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 485 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 486 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 487 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 488 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 489 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 490 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 491 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 492 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 493 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 494 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 495 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 496 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 497 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 498 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 499 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 500 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 501 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 502 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 503 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 504 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 505 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 506 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 507 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 508 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 509 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 510 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 511 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 512 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 513 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 514 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 515 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 516 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 517 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 518 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 519 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 520 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 521 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 522 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 523 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 524 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 525 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 526 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 527 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 528 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 529 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 530 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 531 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 532 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 533 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 534 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 535 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 536 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 537 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 538 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 539 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 540 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 541 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 542 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 543 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 544 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 545 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 546 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 547 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 548 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 549 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 550 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 551 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 552 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 553 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 554 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 555 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 556 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 557 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 558 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 559 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 560 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 561 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 562 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 563 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 564 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 565 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 566 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 567 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 568 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 569 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 570 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 571 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 572 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 573 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 574 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 575 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 576 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 577 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 578 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 579 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 582 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 583 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 586 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 587 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 588 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 589 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 590 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 591 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 592 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 593 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 598 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 599 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 600 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 601 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 602 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 603 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 604 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 605 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 606 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 607 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 608 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 609 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 618 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 619 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 620 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 621 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 624 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 625 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 636 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 637 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 638 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 639 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 640 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 641 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
|
| 646 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
|
| 647 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
|
| 648 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
|
| 649 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
| 650 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 651 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
|
| 652 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 653 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
| 654 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 655 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
| 656 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 657 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 658 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 659 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 660 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 661 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 662 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 663 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 664 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 665 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 666 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 667 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 668 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 669 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 670 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 671 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 672 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 673 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 674 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 675 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 676 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 677 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 678 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 679 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 680 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 681 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 682 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 683 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 684 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 685 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 686 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 687 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 688 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 689 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 690 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 691 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 692 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 693 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 694 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 695 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 696 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 697 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 698 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 699 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 700 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 701 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 702 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 703 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 704 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 705 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 706 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 707 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 708 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 709 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 710 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 711 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 712 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 713 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 714 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 715 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 716 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 717 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 718 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 719 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 720 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 721 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 722 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 723 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 724 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 725 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 726 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 727 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 728 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 729 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 730 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 731 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 732 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 733 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 734 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 735 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 736 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 737 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 738 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 739 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 740 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 741 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 742 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 743 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 744 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 745 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 746 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 747 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 748 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 749 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 750 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 751 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 752 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 753 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
|
| 754 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
|
| 755 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
|
| 756 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
|
| 757 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
|
| 758 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
|
| 759 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
|
| 760 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
|
| 761 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 762 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 763 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
|
| 764 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 765 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 766 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 767 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 768 |
-
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 769 |
-
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
|
| 770 |
-
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
|
| 771 |
-
}
|
| 772 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_2.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/rng_state_3.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:44318e4e5c5027b884cfececcc487f96a157c77de4807e85c07e98cb01ec9bfe
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/special_tokens_map.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>"
|
| 5 |
-
],
|
| 6 |
-
"eos_token": {
|
| 7 |
-
"content": "<|im_end|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"pad_token": {
|
| 14 |
-
"content": "<|endoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
}
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/tokenizer_config.json
DELETED
|
@@ -1,53 +0,0 @@
|
|
| 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": "<image>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
-
"additional_special_tokens": [
|
| 38 |
-
"<|im_start|>",
|
| 39 |
-
"<|im_end|>"
|
| 40 |
-
],
|
| 41 |
-
"bos_token": null,
|
| 42 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 43 |
-
"clean_up_tokenization_spaces": false,
|
| 44 |
-
"eos_token": "<|im_end|>",
|
| 45 |
-
"errors": "replace",
|
| 46 |
-
"model_max_length": 32768,
|
| 47 |
-
"pad_token": "<|endoftext|>",
|
| 48 |
-
"padding_side": "right",
|
| 49 |
-
"processor_class": "LlavaProcessor",
|
| 50 |
-
"split_special_tokens": false,
|
| 51 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 52 |
-
"unk_token": null
|
| 53 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a6f14f1aea2b39bb85650931642a5e57366be81a0b5f9bee5672af7ea86cee97
|
| 3 |
-
size 7864
|
|
|
|
|
|
|
|
|
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-ov_AG_v5_3_split023_fulltune/checkpoint-2500/zero_to_fp32.py
DELETED
|
@@ -1,604 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env python
|
| 2 |
-
|
| 3 |
-
# Copyright (c) Microsoft Corporation.
|
| 4 |
-
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
-
|
| 6 |
-
# DeepSpeed Team
|
| 7 |
-
|
| 8 |
-
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
-
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
-
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
-
# application.
|
| 12 |
-
#
|
| 13 |
-
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
-
|
| 15 |
-
import argparse
|
| 16 |
-
import torch
|
| 17 |
-
import glob
|
| 18 |
-
import math
|
| 19 |
-
import os
|
| 20 |
-
import re
|
| 21 |
-
from collections import OrderedDict
|
| 22 |
-
from dataclasses import dataclass
|
| 23 |
-
|
| 24 |
-
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
-
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
-
from deepspeed.utils import logger
|
| 27 |
-
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
-
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
-
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
@dataclass
|
| 33 |
-
class zero_model_state:
|
| 34 |
-
buffers: dict()
|
| 35 |
-
param_shapes: dict()
|
| 36 |
-
shared_params: list
|
| 37 |
-
ds_version: int
|
| 38 |
-
frozen_param_shapes: dict()
|
| 39 |
-
frozen_param_fragments: dict()
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
debug = 0
|
| 43 |
-
|
| 44 |
-
# load to cpu
|
| 45 |
-
device = torch.device('cpu')
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
def atoi(text):
|
| 49 |
-
return int(text) if text.isdigit() else text
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
def natural_keys(text):
|
| 53 |
-
'''
|
| 54 |
-
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
-
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
-
(See Toothy's implementation in the comments)
|
| 57 |
-
'''
|
| 58 |
-
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
-
if not os.path.isdir(checkpoint_dir):
|
| 63 |
-
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
-
|
| 65 |
-
# there should be only one file
|
| 66 |
-
if zero_stage <= 2:
|
| 67 |
-
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
-
elif zero_stage == 3:
|
| 69 |
-
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
-
|
| 71 |
-
if not os.path.exists(file):
|
| 72 |
-
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
-
|
| 74 |
-
return file
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
-
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
-
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
-
|
| 81 |
-
if len(ckpt_files) == 0:
|
| 82 |
-
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
-
|
| 84 |
-
return ckpt_files
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
def get_optim_files(checkpoint_dir):
|
| 88 |
-
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
def get_model_state_files(checkpoint_dir):
|
| 92 |
-
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
def parse_model_states(files):
|
| 96 |
-
zero_model_states = []
|
| 97 |
-
for file in files:
|
| 98 |
-
state_dict = torch.load(file, map_location=device)
|
| 99 |
-
|
| 100 |
-
if BUFFER_NAMES not in state_dict:
|
| 101 |
-
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
-
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
-
if debug:
|
| 104 |
-
print("Found buffers:", buffer_names)
|
| 105 |
-
|
| 106 |
-
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
-
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
-
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
-
|
| 110 |
-
# collect parameters that are included in param_shapes
|
| 111 |
-
param_names = []
|
| 112 |
-
for s in param_shapes:
|
| 113 |
-
for name in s.keys():
|
| 114 |
-
param_names.append(name)
|
| 115 |
-
|
| 116 |
-
# update with frozen parameters
|
| 117 |
-
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
-
if frozen_param_shapes is not None:
|
| 119 |
-
if debug:
|
| 120 |
-
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
-
param_names += list(frozen_param_shapes.keys())
|
| 122 |
-
|
| 123 |
-
# handle shared params
|
| 124 |
-
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
-
|
| 126 |
-
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
-
|
| 128 |
-
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
-
|
| 130 |
-
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
-
param_shapes=param_shapes,
|
| 132 |
-
shared_params=shared_params,
|
| 133 |
-
ds_version=ds_version,
|
| 134 |
-
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
-
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
-
zero_model_states.append(z_model_state)
|
| 137 |
-
|
| 138 |
-
return zero_model_states
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
-
|
| 143 |
-
total_files = len(files)
|
| 144 |
-
state_dicts = []
|
| 145 |
-
for f in files:
|
| 146 |
-
state_dict = torch.load(f, map_location=device)
|
| 147 |
-
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 148 |
-
# and also handle the case where it was already removed by another helper script
|
| 149 |
-
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 150 |
-
state_dicts.append(state_dict)
|
| 151 |
-
|
| 152 |
-
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 153 |
-
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 154 |
-
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 155 |
-
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 156 |
-
|
| 157 |
-
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 158 |
-
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 159 |
-
# use the max of the partition_count to get the dp world_size.
|
| 160 |
-
|
| 161 |
-
if type(world_size) is list:
|
| 162 |
-
world_size = max(world_size)
|
| 163 |
-
|
| 164 |
-
if world_size != total_files:
|
| 165 |
-
raise ValueError(
|
| 166 |
-
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 167 |
-
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 168 |
-
)
|
| 169 |
-
|
| 170 |
-
# the groups are named differently in each stage
|
| 171 |
-
if zero_stage <= 2:
|
| 172 |
-
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 173 |
-
elif zero_stage == 3:
|
| 174 |
-
fp32_groups_key = FP32_FLAT_GROUPS
|
| 175 |
-
else:
|
| 176 |
-
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 177 |
-
|
| 178 |
-
if zero_stage <= 2:
|
| 179 |
-
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 180 |
-
elif zero_stage == 3:
|
| 181 |
-
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 182 |
-
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 183 |
-
#
|
| 184 |
-
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 185 |
-
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 186 |
-
|
| 187 |
-
fp32_flat_groups = [
|
| 188 |
-
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 189 |
-
]
|
| 190 |
-
|
| 191 |
-
return zero_stage, world_size, fp32_flat_groups
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 195 |
-
"""
|
| 196 |
-
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 197 |
-
|
| 198 |
-
Args:
|
| 199 |
-
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 200 |
-
|
| 201 |
-
"""
|
| 202 |
-
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 203 |
-
|
| 204 |
-
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 205 |
-
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 206 |
-
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 207 |
-
|
| 208 |
-
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 209 |
-
|
| 210 |
-
zero_model_states = parse_model_states(model_files)
|
| 211 |
-
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 212 |
-
|
| 213 |
-
if zero_stage <= 2:
|
| 214 |
-
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 215 |
-
exclude_frozen_parameters)
|
| 216 |
-
elif zero_stage == 3:
|
| 217 |
-
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 218 |
-
exclude_frozen_parameters)
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 222 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 223 |
-
return
|
| 224 |
-
|
| 225 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 226 |
-
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 227 |
-
|
| 228 |
-
if debug:
|
| 229 |
-
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 230 |
-
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 231 |
-
|
| 232 |
-
wanted_params = len(frozen_param_shapes)
|
| 233 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
-
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 235 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 236 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 237 |
-
|
| 238 |
-
total_params = 0
|
| 239 |
-
total_numel = 0
|
| 240 |
-
for name, shape in frozen_param_shapes.items():
|
| 241 |
-
total_params += 1
|
| 242 |
-
unpartitioned_numel = shape.numel()
|
| 243 |
-
total_numel += unpartitioned_numel
|
| 244 |
-
|
| 245 |
-
state_dict[name] = frozen_param_fragments[name]
|
| 246 |
-
|
| 247 |
-
if debug:
|
| 248 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 249 |
-
|
| 250 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
def _has_callable(obj, fn):
|
| 254 |
-
attr = getattr(obj, fn, None)
|
| 255 |
-
return callable(attr)
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 259 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 260 |
-
|
| 261 |
-
# Reconstruction protocol:
|
| 262 |
-
#
|
| 263 |
-
# XXX: document this
|
| 264 |
-
|
| 265 |
-
if debug:
|
| 266 |
-
for i in range(world_size):
|
| 267 |
-
for j in range(len(fp32_flat_groups[0])):
|
| 268 |
-
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 269 |
-
|
| 270 |
-
# XXX: memory usage doubles here (zero2)
|
| 271 |
-
num_param_groups = len(fp32_flat_groups[0])
|
| 272 |
-
merged_single_partition_of_fp32_groups = []
|
| 273 |
-
for i in range(num_param_groups):
|
| 274 |
-
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 275 |
-
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 276 |
-
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 277 |
-
avail_numel = sum(
|
| 278 |
-
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 279 |
-
|
| 280 |
-
if debug:
|
| 281 |
-
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 282 |
-
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 283 |
-
# not asserting if there is a mismatch due to possible padding
|
| 284 |
-
print(f"Have {avail_numel} numels to process.")
|
| 285 |
-
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 286 |
-
|
| 287 |
-
# params
|
| 288 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 289 |
-
# out-of-core computing solution
|
| 290 |
-
total_numel = 0
|
| 291 |
-
total_params = 0
|
| 292 |
-
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 293 |
-
offset = 0
|
| 294 |
-
avail_numel = full_single_fp32_vector.numel()
|
| 295 |
-
for name, shape in shapes.items():
|
| 296 |
-
|
| 297 |
-
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 298 |
-
total_numel += unpartitioned_numel
|
| 299 |
-
total_params += 1
|
| 300 |
-
|
| 301 |
-
if debug:
|
| 302 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 303 |
-
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 304 |
-
offset += unpartitioned_numel
|
| 305 |
-
|
| 306 |
-
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 307 |
-
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 308 |
-
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 309 |
-
# live optimizer object, so we are checking that the numbers are within the right range
|
| 310 |
-
align_to = 2 * world_size
|
| 311 |
-
|
| 312 |
-
def zero2_align(x):
|
| 313 |
-
return align_to * math.ceil(x / align_to)
|
| 314 |
-
|
| 315 |
-
if debug:
|
| 316 |
-
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 317 |
-
|
| 318 |
-
offset = zero2_align(offset)
|
| 319 |
-
avail_numel = zero2_align(avail_numel)
|
| 320 |
-
|
| 321 |
-
if debug:
|
| 322 |
-
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 323 |
-
|
| 324 |
-
# Sanity check
|
| 325 |
-
if offset != avail_numel:
|
| 326 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 327 |
-
|
| 328 |
-
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 329 |
-
|
| 330 |
-
|
| 331 |
-
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 332 |
-
exclude_frozen_parameters):
|
| 333 |
-
state_dict = OrderedDict()
|
| 334 |
-
|
| 335 |
-
# buffers
|
| 336 |
-
buffers = zero_model_states[0].buffers
|
| 337 |
-
state_dict.update(buffers)
|
| 338 |
-
if debug:
|
| 339 |
-
print(f"added {len(buffers)} buffers")
|
| 340 |
-
|
| 341 |
-
if not exclude_frozen_parameters:
|
| 342 |
-
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 343 |
-
|
| 344 |
-
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 345 |
-
|
| 346 |
-
# recover shared parameters
|
| 347 |
-
for pair in zero_model_states[0].shared_params:
|
| 348 |
-
if pair[1] in state_dict:
|
| 349 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 350 |
-
|
| 351 |
-
return state_dict
|
| 352 |
-
|
| 353 |
-
|
| 354 |
-
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 355 |
-
remainder = unpartitioned_numel % world_size
|
| 356 |
-
padding_numel = (world_size - remainder) if remainder else 0
|
| 357 |
-
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 358 |
-
return partitioned_numel, padding_numel
|
| 359 |
-
|
| 360 |
-
|
| 361 |
-
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 362 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 363 |
-
return
|
| 364 |
-
|
| 365 |
-
if debug:
|
| 366 |
-
for i in range(world_size):
|
| 367 |
-
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 368 |
-
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 369 |
-
|
| 370 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 371 |
-
wanted_params = len(frozen_param_shapes)
|
| 372 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 373 |
-
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 374 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 375 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 376 |
-
|
| 377 |
-
total_params = 0
|
| 378 |
-
total_numel = 0
|
| 379 |
-
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 380 |
-
total_params += 1
|
| 381 |
-
unpartitioned_numel = shape.numel()
|
| 382 |
-
total_numel += unpartitioned_numel
|
| 383 |
-
|
| 384 |
-
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 385 |
-
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 386 |
-
|
| 387 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 388 |
-
|
| 389 |
-
if debug:
|
| 390 |
-
print(
|
| 391 |
-
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 392 |
-
)
|
| 393 |
-
|
| 394 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 395 |
-
|
| 396 |
-
|
| 397 |
-
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 398 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 399 |
-
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 400 |
-
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 401 |
-
# param, re-consolidating each param, while dealing with padding if any
|
| 402 |
-
|
| 403 |
-
# merge list of dicts, preserving order
|
| 404 |
-
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 405 |
-
|
| 406 |
-
if debug:
|
| 407 |
-
for i in range(world_size):
|
| 408 |
-
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 409 |
-
|
| 410 |
-
wanted_params = len(param_shapes)
|
| 411 |
-
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 412 |
-
# not asserting if there is a mismatch due to possible padding
|
| 413 |
-
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 414 |
-
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 415 |
-
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 416 |
-
|
| 417 |
-
# params
|
| 418 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 419 |
-
# out-of-core computing solution
|
| 420 |
-
offset = 0
|
| 421 |
-
total_numel = 0
|
| 422 |
-
total_params = 0
|
| 423 |
-
for name, shape in param_shapes.items():
|
| 424 |
-
|
| 425 |
-
unpartitioned_numel = shape.numel()
|
| 426 |
-
total_numel += unpartitioned_numel
|
| 427 |
-
total_params += 1
|
| 428 |
-
|
| 429 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 430 |
-
|
| 431 |
-
if debug:
|
| 432 |
-
print(
|
| 433 |
-
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 434 |
-
)
|
| 435 |
-
|
| 436 |
-
# XXX: memory usage doubles here
|
| 437 |
-
state_dict[name] = torch.cat(
|
| 438 |
-
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 439 |
-
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 440 |
-
offset += partitioned_numel
|
| 441 |
-
|
| 442 |
-
offset *= world_size
|
| 443 |
-
|
| 444 |
-
# Sanity check
|
| 445 |
-
if offset != avail_numel:
|
| 446 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 447 |
-
|
| 448 |
-
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 449 |
-
|
| 450 |
-
|
| 451 |
-
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 452 |
-
exclude_frozen_parameters):
|
| 453 |
-
state_dict = OrderedDict()
|
| 454 |
-
|
| 455 |
-
# buffers
|
| 456 |
-
buffers = zero_model_states[0].buffers
|
| 457 |
-
state_dict.update(buffers)
|
| 458 |
-
if debug:
|
| 459 |
-
print(f"added {len(buffers)} buffers")
|
| 460 |
-
|
| 461 |
-
if not exclude_frozen_parameters:
|
| 462 |
-
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 463 |
-
|
| 464 |
-
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 465 |
-
|
| 466 |
-
# recover shared parameters
|
| 467 |
-
for pair in zero_model_states[0].shared_params:
|
| 468 |
-
if pair[1] in state_dict:
|
| 469 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 470 |
-
|
| 471 |
-
return state_dict
|
| 472 |
-
|
| 473 |
-
|
| 474 |
-
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 475 |
-
"""
|
| 476 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 477 |
-
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 478 |
-
via a model hub.
|
| 479 |
-
|
| 480 |
-
Args:
|
| 481 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 482 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 483 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 484 |
-
|
| 485 |
-
Returns:
|
| 486 |
-
- pytorch ``state_dict``
|
| 487 |
-
|
| 488 |
-
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 489 |
-
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 490 |
-
the checkpoint.
|
| 491 |
-
|
| 492 |
-
A typical usage might be ::
|
| 493 |
-
|
| 494 |
-
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 495 |
-
# do the training and checkpoint saving
|
| 496 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 497 |
-
model = model.cpu() # move to cpu
|
| 498 |
-
model.load_state_dict(state_dict)
|
| 499 |
-
# submit to model hub or save the model to share with others
|
| 500 |
-
|
| 501 |
-
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 502 |
-
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 503 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 504 |
-
|
| 505 |
-
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 506 |
-
|
| 507 |
-
"""
|
| 508 |
-
if tag is None:
|
| 509 |
-
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 510 |
-
if os.path.isfile(latest_path):
|
| 511 |
-
with open(latest_path, 'r') as fd:
|
| 512 |
-
tag = fd.read().strip()
|
| 513 |
-
else:
|
| 514 |
-
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 515 |
-
|
| 516 |
-
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 517 |
-
|
| 518 |
-
if not os.path.isdir(ds_checkpoint_dir):
|
| 519 |
-
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 520 |
-
|
| 521 |
-
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 522 |
-
|
| 523 |
-
|
| 524 |
-
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
| 525 |
-
"""
|
| 526 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 527 |
-
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 528 |
-
|
| 529 |
-
Args:
|
| 530 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 531 |
-
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 532 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 533 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 534 |
-
"""
|
| 535 |
-
|
| 536 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 537 |
-
print(f"Saving fp32 state dict to {output_file}")
|
| 538 |
-
torch.save(state_dict, output_file)
|
| 539 |
-
|
| 540 |
-
|
| 541 |
-
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 542 |
-
"""
|
| 543 |
-
1. Put the provided model to cpu
|
| 544 |
-
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 545 |
-
3. Load it into the provided model
|
| 546 |
-
|
| 547 |
-
Args:
|
| 548 |
-
- ``model``: the model object to update
|
| 549 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 550 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 551 |
-
|
| 552 |
-
Returns:
|
| 553 |
-
- ``model`: modified model
|
| 554 |
-
|
| 555 |
-
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 556 |
-
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 557 |
-
conveniently placed for you in the checkpoint folder.
|
| 558 |
-
|
| 559 |
-
A typical usage might be ::
|
| 560 |
-
|
| 561 |
-
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 562 |
-
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 563 |
-
# submit to model hub or save the model to share with others
|
| 564 |
-
|
| 565 |
-
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 566 |
-
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 567 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 568 |
-
|
| 569 |
-
"""
|
| 570 |
-
logger.info(f"Extracting fp32 weights")
|
| 571 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 572 |
-
|
| 573 |
-
logger.info(f"Overwriting model with fp32 weights")
|
| 574 |
-
model = model.cpu()
|
| 575 |
-
model.load_state_dict(state_dict, strict=False)
|
| 576 |
-
|
| 577 |
-
return model
|
| 578 |
-
|
| 579 |
-
|
| 580 |
-
if __name__ == "__main__":
|
| 581 |
-
|
| 582 |
-
parser = argparse.ArgumentParser()
|
| 583 |
-
parser.add_argument("checkpoint_dir",
|
| 584 |
-
type=str,
|
| 585 |
-
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 586 |
-
parser.add_argument(
|
| 587 |
-
"output_file",
|
| 588 |
-
type=str,
|
| 589 |
-
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 590 |
-
parser.add_argument("-t",
|
| 591 |
-
"--tag",
|
| 592 |
-
type=str,
|
| 593 |
-
default=None,
|
| 594 |
-
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 595 |
-
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 596 |
-
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 597 |
-
args = parser.parse_args()
|
| 598 |
-
|
| 599 |
-
debug = args.debug
|
| 600 |
-
|
| 601 |
-
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 602 |
-
args.output_file,
|
| 603 |
-
tag=args.tag,
|
| 604 |
-
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|