Hugging Face's logo

zixianma
/
mma_mantis_from_tuned_293k-seq_len_8192-lr_1e-5-gl_bs_128-ep_2

Safetensors
llava
Generated from Trainer
Model card Files Community
zixianma commited on
Commit
57f3f91
•
1 Parent(s): c56c7de

Delete checkpoint-4578

Browse files
Files changed (40) hide show
  1. checkpoint-4578/config.json +0 -43
  2. checkpoint-4578/generation_config.json +0 -7
  3. checkpoint-4578/global_step4578/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
  4. checkpoint-4578/global_step4578/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
  5. checkpoint-4578/global_step4578/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
  6. checkpoint-4578/global_step4578/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
  7. checkpoint-4578/global_step4578/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -3
  8. checkpoint-4578/global_step4578/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -3
  9. checkpoint-4578/global_step4578/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -3
  10. checkpoint-4578/global_step4578/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -3
  11. checkpoint-4578/global_step4578/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
  12. checkpoint-4578/global_step4578/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
  13. checkpoint-4578/global_step4578/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
  14. checkpoint-4578/global_step4578/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
  15. checkpoint-4578/global_step4578/zero_pp_rank_4_mp_rank_00_model_states.pt +0 -3
  16. checkpoint-4578/global_step4578/zero_pp_rank_5_mp_rank_00_model_states.pt +0 -3
  17. checkpoint-4578/global_step4578/zero_pp_rank_6_mp_rank_00_model_states.pt +0 -3
  18. checkpoint-4578/global_step4578/zero_pp_rank_7_mp_rank_00_model_states.pt +0 -3
  19. checkpoint-4578/latest +0 -1
  20. checkpoint-4578/model-00001-of-00004.safetensors +0 -3
  21. checkpoint-4578/model-00002-of-00004.safetensors +0 -3
  22. checkpoint-4578/model-00003-of-00004.safetensors +0 -3
  23. checkpoint-4578/model-00004-of-00004.safetensors +0 -3
  24. checkpoint-4578/model.safetensors.index.json +0 -750
  25. checkpoint-4578/preprocessor_config.json +0 -24
  26. checkpoint-4578/rng_state_0.pth +0 -3
  27. checkpoint-4578/rng_state_1.pth +0 -3
  28. checkpoint-4578/rng_state_2.pth +0 -3
  29. checkpoint-4578/rng_state_3.pth +0 -3
  30. checkpoint-4578/rng_state_4.pth +0 -3
  31. checkpoint-4578/rng_state_5.pth +0 -3
  32. checkpoint-4578/rng_state_6.pth +0 -3
  33. checkpoint-4578/rng_state_7.pth +0 -3
  34. checkpoint-4578/scheduler.pt +0 -3
  35. checkpoint-4578/special_tokens_map.json +0 -27
  36. checkpoint-4578/tokenizer.json +0 -0
  37. checkpoint-4578/tokenizer_config.json +0 -2097
  38. checkpoint-4578/trainer_state.json +0 -0
  39. checkpoint-4578/training_args.bin +0 -3
  40. checkpoint-4578/zero_to_fp32.py +0 -604
checkpoint-4578/config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "_name_or_path": "TIGER-Lab/Mantis-8B-siglip-llama3",
3
- "architectures": [
4
- "LlavaForConditionalGeneration"
5
- ],
6
- "ignore_index": -100,
7
- "image_token_index": 128256,
8
- "model_type": "llava",
9
- "pad_token_id": 128257,
10
- "projector_hidden_act": "gelu",
11
- "text_config": {
12
- "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
13
- "architectures": [
14
- "LlamaForCausalLM"
15
- ],
16
- "bos_token_id": 128000,
17
- "eos_token_id": 128001,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 8192,
20
- "model_type": "llama",
21
- "num_key_value_heads": 8,
22
- "rms_norm_eps": 1e-05,
23
- "rope_theta": 500000.0,
24
- "torch_dtype": "bfloat16",
25
- "vocab_size": 128258
26
- },
27
- "torch_dtype": "bfloat16",
28
- "transformers_version": "4.43.0",
29
- "vision_config": {
30
- "hidden_act": "gelu_pytorch_tanh",
31
- "hidden_size": 1152,
32
- "image_size": 384,
33
- "intermediate_size": 4304,
34
- "layer_norm_eps": 1e-06,
35
- "model_type": "siglip_vision_model",
36
- "num_attention_heads": 16,
37
- "num_hidden_layers": 27,
38
- "patch_size": 14
39
- },
40
- "vision_feature_layer": -2,
41
- "vision_feature_select_strategy": "default",
42
- "vocab_size": 128258
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4578/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 128000,
4
- "eos_token_id": 128001,
5
- "pad_token_id": 128257,
6
- "transformers_version": "4.43.0"
7
- }
 
 
 
 
 
 
 
 
checkpoint-4578/global_step4578/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 sha256:8f5c10dc670a5bbc7f9e8b40ad442285e1d8db732afc95fc4a11fd0003444830
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/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:a7dc6f0b760b3a0c71f34f07b4c254f0e99c2762bc32f9d7b948985c62334d40
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/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 sha256:109a817dd58b7a2a157ed534ab74abb72864ee7719a63de077114c5dd0ad94b1
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/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:a620b7e68d40cb7a4814a7a0a965ebac347f608a43b5530f83594ece6634be53
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ba1e27c21a587a1c074cfbc3c8128da01e6780eb3dc8d93255e4645ea1cb6ea
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2253e8385ad009a1ea5d5ea0f9a973eb395a4ecee7b01675af9bac5954e52a37
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:68c1013131b741611f144c232527f375ffe55d61f818a0cdd7fc5da35dafdaab
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:db1830e0a2fe86d39f440fa0f8db51b33b65f708b5dbc22d5427f8cf86739f51
3
- size 12077677388
 
 
 
 
checkpoint-4578/global_step4578/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 sha256:59e40311ac8604028415d0c180e03cd33b2989d474dd2789358c39f38e301a58
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/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:a727924c68b8e59a79be16ae09b04c354d04bd024e8aa6f4a1129f3aa2574d0e
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/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 sha256:51a19dcc5e85fbcb524c29cc506e5544234febb699812b1f63c9ebd9f1f1ad67
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/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 sha256:269128ef0908c2244efb91736cacc183193cfcbb155c40278c6781f1f6693040
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/zero_pp_rank_4_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8935eb30485c5b2e6769391258a3ddfdfd408c3f88d4320f8ffad12b7c4eee12
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/zero_pp_rank_5_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7e0cf1ca74cd8027f6245b6f36042ab9b71d0e3b559b10fe1cd2d539cd12ed4
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/zero_pp_rank_6_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d44650528f65fbad527578199d9680eac417e3fdfe9a0ea536e98f0a341214f5
3
- size 107608280
 
 
 
 
checkpoint-4578/global_step4578/zero_pp_rank_7_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a36b14a8ea37b3f83484600e99ac3ec76bf09dc74cd628cd5d380067d0b15dc7
3
- size 107608280
 
 
 
 
checkpoint-4578/latest DELETED
@@ -1 +0,0 @@
1
- global_step4578
 
 
checkpoint-4578/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a5f8557f604e267c11833d7cfded7214d0c0ab31ecadcec1dca6495ef99557
3
- size 4886330032
 
 
 
 
checkpoint-4578/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce32b51834049fe0270f18abdf1899f4b99638b70c160cdb17c344016dd8b440
3
- size 4999820904
 
 
 
 
checkpoint-4578/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:baa8572c22b7f6fd2df67143772861cef0669e021576b608793a251c5b4a64a0
3
- size 4915917680
 
 
 
 
checkpoint-4578/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa4e5d0e9c1de595916fd412597cdb77140ddf919019b96ae06a8995d9715630
3
- size 2158046280
 
 
 
 
checkpoint-4578/model.safetensors.index.json DELETED
@@ -1,750 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 16960014464
4
- },
5
- "weight_map": {
6
- "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
7
- "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
- "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
- "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
- "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
- "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
- "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
- "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
- "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
- "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
- "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
- "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
- "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
- "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
- "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
- "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
- "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
- "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
- "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
- "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
- "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
- "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
- "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
- "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
- "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
- "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
- "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
- "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
- "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
- "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
- "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
- "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
- "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
- "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
- "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
- "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
- "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
- "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
- "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
- "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
- "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
- "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
- "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
- "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
- "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
- "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
- "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
- "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
- "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
- "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
- "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
- "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
- "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
- "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
- "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
- "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
- "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
- "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
- "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
- "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
- "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
- "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
- "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
- "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
- "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
- "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
- "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
- "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
- "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
- "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
- "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
- "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
- "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
- "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
- "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
- "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
- "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
- "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
- "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
- "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
- "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
- "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
- "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
- "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
- "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
- "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
- "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
- "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
- "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
101
- "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
102
- "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
103
- "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
- "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
- "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
- "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
- "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
- "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
- "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
- "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
- "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
- "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
113
- "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
114
- "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
115
- "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
116
- "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
- "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
- "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
- "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
- "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
- "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
- "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
- "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
- "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
- "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
- "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
- "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
- "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
- "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
- "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
- "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
- "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
- "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
- "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
- "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
- "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
- "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
- "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
- "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
- "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
- "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
- "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
- "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
- "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
- "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
- "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
- "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
- "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
- "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
- "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
- "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
- "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
- "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
- "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
- "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
- "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
- "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
- "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
- "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
- "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
- "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
- "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
- "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
- "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
- "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
- "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
- "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
- "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
- "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
- "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
- "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
- "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
- "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
- "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
- "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
- "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
- "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
- "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
- "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
- "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
- "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
- "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
- "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
- "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
- "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
- "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
- "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
- "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
- "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
- "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
- "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
- "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
- "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
- "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
- "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
- "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
- "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
- "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
- "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
- "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
- "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
- "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
- "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
- "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
- "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
207
- "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
208
- "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
- "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
210
- "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
211
- "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
- "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
- "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
- "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
- "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
- "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
- "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
- "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
- "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
- "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
- "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
- "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
- "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
- "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
225
- "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
226
- "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
227
- "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
228
- "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
229
- "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
230
- "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
231
- "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
232
- "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
233
- "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
- "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
- "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
236
- "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
237
- "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
- "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
239
- "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
240
- "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
241
- "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
242
- "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
- "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
- "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
- "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
- "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
- "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
- "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
- "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
- "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
- "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
- "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
- "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
- "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
- "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
- "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
- "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
261
- "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
262
- "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
- "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
- "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
265
- "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
- "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
- "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
- "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
- "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
270
- "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
271
- "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
272
- "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
273
- "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
274
- "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
275
- "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
276
- "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
277
- "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
278
- "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
279
- "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
280
- "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
281
- "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
282
- "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
283
- "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
284
- "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
285
- "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
286
- "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
287
- "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
- "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
- "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
- "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
- "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
- "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
- "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
- "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
- "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
- "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
297
- "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
298
- "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
299
- "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
300
- "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
301
- "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
302
- "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
303
- "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
304
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
305
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
306
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
307
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
308
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
309
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
310
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
311
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
312
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
313
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
314
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
315
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
316
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
321
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
322
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
323
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
324
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
325
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
326
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
327
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
328
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
329
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
330
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
331
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
332
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
333
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
334
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
335
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
336
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
337
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
338
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
339
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
340
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
341
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
342
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
343
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
344
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
345
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
347
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
348
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
349
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
350
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
351
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
352
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
353
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
354
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
355
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
356
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
357
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
358
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
359
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
360
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
361
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
362
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
363
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
364
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
365
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
366
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
367
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
368
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
369
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
370
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
371
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
372
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
373
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
374
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
375
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
376
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
377
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
378
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
379
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
380
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
381
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
383
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
384
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
385
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
386
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
387
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
388
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
389
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
390
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
391
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
392
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
393
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
394
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
395
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
396
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
397
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
398
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
399
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
400
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
401
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
402
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
403
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
404
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
405
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
406
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
407
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
408
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
409
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
410
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
411
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
412
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
413
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
414
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
415
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
416
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
417
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
418
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
419
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
420
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
421
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
422
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
423
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
424
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
425
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
426
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
427
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
428
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
429
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
430
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
431
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
432
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
433
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
434
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
435
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
436
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
437
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
438
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
439
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
440
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
441
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
442
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
443
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
444
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
445
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
446
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
447
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
448
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
449
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
450
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
451
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
452
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
453
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
454
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
455
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
456
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
457
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
458
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
459
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
460
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
461
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
462
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
463
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
464
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
465
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
466
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
467
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
468
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
469
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
470
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
471
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
472
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
473
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
474
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
475
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
476
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
477
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
478
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
479
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
480
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
481
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
482
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
483
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
484
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
485
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
486
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
487
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
488
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
489
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
490
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
491
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
492
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
493
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
494
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
495
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
496
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
497
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
498
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
499
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
500
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
501
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
502
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
503
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
504
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
505
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
506
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
507
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
508
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
509
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
510
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
511
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
512
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
513
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
514
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
515
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
516
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
517
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
518
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
519
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
520
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
521
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
522
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
523
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
524
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
525
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
526
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
527
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
528
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
529
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
530
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
531
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
532
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
533
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
534
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
535
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
536
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
537
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
538
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
539
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
540
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
541
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
542
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
543
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
544
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
545
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
546
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
547
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
548
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
549
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
550
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
551
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
552
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
553
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
554
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
555
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
556
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
557
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
558
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
559
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
560
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
561
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
562
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
563
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
564
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
565
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
566
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
567
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
568
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
569
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
570
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
571
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
572
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
573
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
574
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
575
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
576
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
577
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
578
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
579
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
580
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
581
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
582
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
583
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
584
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
585
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
586
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
587
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
588
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
589
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
590
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
591
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
592
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
593
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
594
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
595
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
596
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
597
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
598
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
599
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
600
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
601
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
602
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
603
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
604
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
605
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
606
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
607
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
608
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
609
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
610
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
611
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
612
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
613
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
614
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
615
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
616
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
617
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
618
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
619
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
620
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
621
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
622
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
623
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
624
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
625
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
626
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
627
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
628
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
629
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
630
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
631
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
632
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
633
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
634
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
635
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
636
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
637
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
638
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
639
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
640
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
641
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
642
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
643
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
644
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
645
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
646
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
647
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
648
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
649
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
650
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
651
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
652
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
653
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
654
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
655
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
656
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
657
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
658
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
659
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
660
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
661
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
662
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
663
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
664
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
665
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
666
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
667
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
668
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
669
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
670
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
671
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
672
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
673
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
674
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
675
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
676
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
677
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
678
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
679
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
680
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
681
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
682
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
683
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
684
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
685
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
686
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
687
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
688
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
689
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
690
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
691
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
692
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
693
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
694
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
695
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
696
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
697
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
698
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
699
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
700
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
701
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
702
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
703
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
704
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
705
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
706
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
707
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
708
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
709
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
710
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
711
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
712
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
713
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
714
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
715
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
716
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
717
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
718
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
719
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
720
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
721
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
722
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
723
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
724
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
725
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
726
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
727
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
728
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
729
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
730
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
731
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
732
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
733
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
734
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
735
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
736
- "vision_tower.vision_model.head.attention.in_proj_bias": "model-00001-of-00004.safetensors",
737
- "vision_tower.vision_model.head.attention.in_proj_weight": "model-00001-of-00004.safetensors",
738
- "vision_tower.vision_model.head.attention.out_proj.bias": "model-00001-of-00004.safetensors",
739
- "vision_tower.vision_model.head.attention.out_proj.weight": "model-00001-of-00004.safetensors",
740
- "vision_tower.vision_model.head.layernorm.bias": "model-00001-of-00004.safetensors",
741
- "vision_tower.vision_model.head.layernorm.weight": "model-00001-of-00004.safetensors",
742
- "vision_tower.vision_model.head.mlp.fc1.bias": "model-00001-of-00004.safetensors",
743
- "vision_tower.vision_model.head.mlp.fc1.weight": "model-00001-of-00004.safetensors",
744
- "vision_tower.vision_model.head.mlp.fc2.bias": "model-00001-of-00004.safetensors",
745
- "vision_tower.vision_model.head.mlp.fc2.weight": "model-00001-of-00004.safetensors",
746
- "vision_tower.vision_model.head.probe": "model-00001-of-00004.safetensors",
747
- "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
748
- "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
749
- }
750
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4578/preprocessor_config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "do_convert_rgb": null,
3
- "do_normalize": true,
4
- "do_rescale": true,
5
- "do_resize": true,
6
- "image_mean": [
7
- 0.5,
8
- 0.5,
9
- 0.5
10
- ],
11
- "image_processor_type": "SiglipImageProcessor",
12
- "image_std": [
13
- 0.5,
14
- 0.5,
15
- 0.5
16
- ],
17
- "processor_class": "MLlavaProcessor",
18
- "resample": 3,
19
- "rescale_factor": 0.00392156862745098,
20
- "size": {
21
- "height": 384,
22
- "width": 384
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4578/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
3
- size 15984
 
 
 
 
checkpoint-4578/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
3
- size 15984
 
 
 
 
checkpoint-4578/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0cb49fe1820785142154eeb75df4666048815b95664498ad6a35bc34409d0c6
3
- size 1064
 
 
 
 
checkpoint-4578/special_tokens_map.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<image>",
4
- "<|pad|>"
5
- ],
6
- "bos_token": {
7
- "content": "<|begin_of_text|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "eos_token": {
14
- "content": "<|end_of_text|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "unk_token": {
21
- "content": "<unk>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4578/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-4578/tokenizer_config.json DELETED
@@ -1,2097 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "128000": {
7
- "content": "<|begin_of_text|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "128001": {
15
- "content": "<|end_of_text|>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "128002": {
23
- "content": "<|reserved_special_token_0|>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- },
30
- "128003": {
31
- "content": "<|reserved_special_token_1|>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": true
37
- },
38
- "128004": {
39
- "content": "<|reserved_special_token_2|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false,
44
- "special": true
45
- },
46
- "128005": {
47
- "content": "<|reserved_special_token_3|>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": false,
51
- "single_word": false,
52
- "special": true
53
- },
54
- "128006": {
55
- "content": "<|start_header_id|>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": false,
59
- "single_word": false,
60
- "special": true
61
- },
62
- "128007": {
63
- "content": "<|end_header_id|>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": false,
67
- "single_word": false,
68
- "special": true
69
- },
70
- "128008": {
71
- "content": "<|reserved_special_token_4|>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": false,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "128009": {
79
- "content": "<|eot_id|>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": false,
83
- "single_word": false,
84
- "special": true
85
- },
86
- "128010": {
87
- "content": "<|reserved_special_token_5|>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": false,
91
- "single_word": false,
92
- "special": true
93
- },
94
- "128011": {
95
- "content": "<|reserved_special_token_6|>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": false,
99
- "single_word": false,
100
- "special": true
101
- },
102
- "128012": {
103
- "content": "<|reserved_special_token_7|>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": false,
107
- "single_word": false,
108
- "special": true
109
- },
110
- "128013": {
111
- "content": "<|reserved_special_token_8|>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": false,
115
- "single_word": false,
116
- "special": true
117
- },
118
- "128014": {
119
- "content": "<|reserved_special_token_9|>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false,
124
- "special": true
125
- },
126
- "128015": {
127
- "content": "<|reserved_special_token_10|>",
128
- "lstrip": false,
129
- "normalized": false,
130
- "rstrip": false,
131
- "single_word": false,
132
- "special": true
133
- },
134
- "128016": {
135
- "content": "<|reserved_special_token_11|>",
136
- "lstrip": false,
137
- "normalized": false,
138
- "rstrip": false,
139
- "single_word": false,
140
- "special": true
141
- },
142
- "128017": {
143
- "content": "<|reserved_special_token_12|>",
144
- "lstrip": false,
145
- "normalized": false,
146
- "rstrip": false,
147
- "single_word": false,
148
- "special": true
149
- },
150
- "128018": {
151
- "content": "<|reserved_special_token_13|>",
152
- "lstrip": false,
153
- "normalized": false,
154
- "rstrip": false,
155
- "single_word": false,
156
- "special": true
157
- },
158
- "128019": {
159
- "content": "<|reserved_special_token_14|>",
160
- "lstrip": false,
161
- "normalized": false,
162
- "rstrip": false,
163
- "single_word": false,
164
- "special": true
165
- },
166
- "128020": {
167
- "content": "<|reserved_special_token_15|>",
168
- "lstrip": false,
169
- "normalized": false,
170
- "rstrip": false,
171
- "single_word": false,
172
- "special": true
173
- },
174
- "128021": {
175
- "content": "<|reserved_special_token_16|>",
176
- "lstrip": false,
177
- "normalized": false,
178
- "rstrip": false,
179
- "single_word": false,
180
- "special": true
181
- },
182
- "128022": {
183
- "content": "<|reserved_special_token_17|>",
184
- "lstrip": false,
185
- "normalized": false,
186
- "rstrip": false,
187
- "single_word": false,
188
- "special": true
189
- },
190
- "128023": {
191
- "content": "<|reserved_special_token_18|>",
192
- "lstrip": false,
193
- "normalized": false,
194
- "rstrip": false,
195
- "single_word": false,
196
- "special": true
197
- },
198
- "128024": {
199
- "content": "<|reserved_special_token_19|>",
200
- "lstrip": false,
201
- "normalized": false,
202
- "rstrip": false,
203
- "single_word": false,
204
- "special": true
205
- },
206
- "128025": {
207
- "content": "<|reserved_special_token_20|>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false,
212
- "special": true
213
- },
214
- "128026": {
215
- "content": "<|reserved_special_token_21|>",
216
- "lstrip": false,
217
- "normalized": false,
218
- "rstrip": false,
219
- "single_word": false,
220
- "special": true
221
- },
222
- "128027": {
223
- "content": "<|reserved_special_token_22|>",
224
- "lstrip": false,
225
- "normalized": false,
226
- "rstrip": false,
227
- "single_word": false,
228
- "special": true
229
- },
230
- "128028": {
231
- "content": "<|reserved_special_token_23|>",
232
- "lstrip": false,
233
- "normalized": false,
234
- "rstrip": false,
235
- "single_word": false,
236
- "special": true
237
- },
238
- "128029": {
239
- "content": "<|reserved_special_token_24|>",
240
- "lstrip": false,
241
- "normalized": false,
242
- "rstrip": false,
243
- "single_word": false,
244
- "special": true
245
- },
246
- "128030": {
247
- "content": "<|reserved_special_token_25|>",
248
- "lstrip": false,
249
- "normalized": false,
250
- "rstrip": false,
251
- "single_word": false,
252
- "special": true
253
- },
254
- "128031": {
255
- "content": "<|reserved_special_token_26|>",
256
- "lstrip": false,
257
- "normalized": false,
258
- "rstrip": false,
259
- "single_word": false,
260
- "special": true
261
- },
262
- "128032": {
263
- "content": "<|reserved_special_token_27|>",
264
- "lstrip": false,
265
- "normalized": false,
266
- "rstrip": false,
267
- "single_word": false,
268
- "special": true
269
- },
270
- "128033": {
271
- "content": "<|reserved_special_token_28|>",
272
- "lstrip": false,
273
- "normalized": false,
274
- "rstrip": false,
275
- "single_word": false,
276
- "special": true
277
- },
278
- "128034": {
279
- "content": "<|reserved_special_token_29|>",
280
- "lstrip": false,
281
- "normalized": false,
282
- "rstrip": false,
283
- "single_word": false,
284
- "special": true
285
- },
286
- "128035": {
287
- "content": "<|reserved_special_token_30|>",
288
- "lstrip": false,
289
- "normalized": false,
290
- "rstrip": false,
291
- "single_word": false,
292
- "special": true
293
- },
294
- "128036": {
295
- "content": "<|reserved_special_token_31|>",
296
- "lstrip": false,
297
- "normalized": false,
298
- "rstrip": false,
299
- "single_word": false,
300
- "special": true
301
- },
302
- "128037": {
303
- "content": "<|reserved_special_token_32|>",
304
- "lstrip": false,
305
- "normalized": false,
306
- "rstrip": false,
307
- "single_word": false,
308
- "special": true
309
- },
310
- "128038": {
311
- "content": "<|reserved_special_token_33|>",
312
- "lstrip": false,
313
- "normalized": false,
314
- "rstrip": false,
315
- "single_word": false,
316
- "special": true
317
- },
318
- "128039": {
319
- "content": "<|reserved_special_token_34|>",
320
- "lstrip": false,
321
- "normalized": false,
322
- "rstrip": false,
323
- "single_word": false,
324
- "special": true
325
- },
326
- "128040": {
327
- "content": "<|reserved_special_token_35|>",
328
- "lstrip": false,
329
- "normalized": false,
330
- "rstrip": false,
331
- "single_word": false,
332
- "special": true
333
- },
334
- "128041": {
335
- "content": "<|reserved_special_token_36|>",
336
- "lstrip": false,
337
- "normalized": false,
338
- "rstrip": false,
339
- "single_word": false,
340
- "special": true
341
- },
342
- "128042": {
343
- "content": "<|reserved_special_token_37|>",
344
- "lstrip": false,
345
- "normalized": false,
346
- "rstrip": false,
347
- "single_word": false,
348
- "special": true
349
- },
350
- "128043": {
351
- "content": "<|reserved_special_token_38|>",
352
- "lstrip": false,
353
- "normalized": false,
354
- "rstrip": false,
355
- "single_word": false,
356
- "special": true
357
- },
358
- "128044": {
359
- "content": "<|reserved_special_token_39|>",
360
- "lstrip": false,
361
- "normalized": false,
362
- "rstrip": false,
363
- "single_word": false,
364
- "special": true
365
- },
366
- "128045": {
367
- "content": "<|reserved_special_token_40|>",
368
- "lstrip": false,
369
- "normalized": false,
370
- "rstrip": false,
371
- "single_word": false,
372
- "special": true
373
- },
374
- "128046": {
375
- "content": "<|reserved_special_token_41|>",
376
- "lstrip": false,
377
- "normalized": false,
378
- "rstrip": false,
379
- "single_word": false,
380
- "special": true
381
- },
382
- "128047": {
383
- "content": "<|reserved_special_token_42|>",
384
- "lstrip": false,
385
- "normalized": false,
386
- "rstrip": false,
387
- "single_word": false,
388
- "special": true
389
- },
390
- "128048": {
391
- "content": "<|reserved_special_token_43|>",
392
- "lstrip": false,
393
- "normalized": false,
394
- "rstrip": false,
395
- "single_word": false,
396
- "special": true
397
- },
398
- "128049": {
399
- "content": "<|reserved_special_token_44|>",
400
- "lstrip": false,
401
- "normalized": false,
402
- "rstrip": false,
403
- "single_word": false,
404
- "special": true
405
- },
406
- "128050": {
407
- "content": "<|reserved_special_token_45|>",
408
- "lstrip": false,
409
- "normalized": false,
410
- "rstrip": false,
411
- "single_word": false,
412
- "special": true
413
- },
414
- "128051": {
415
- "content": "<|reserved_special_token_46|>",
416
- "lstrip": false,
417
- "normalized": false,
418
- "rstrip": false,
419
- "single_word": false,
420
- "special": true
421
- },
422
- "128052": {
423
- "content": "<|reserved_special_token_47|>",
424
- "lstrip": false,
425
- "normalized": false,
426
- "rstrip": false,
427
- "single_word": false,
428
- "special": true
429
- },
430
- "128053": {
431
- "content": "<|reserved_special_token_48|>",
432
- "lstrip": false,
433
- "normalized": false,
434
- "rstrip": false,
435
- "single_word": false,
436
- "special": true
437
- },
438
- "128054": {
439
- "content": "<|reserved_special_token_49|>",
440
- "lstrip": false,
441
- "normalized": false,
442
- "rstrip": false,
443
- "single_word": false,
444
- "special": true
445
- },
446
- "128055": {
447
- "content": "<|reserved_special_token_50|>",
448
- "lstrip": false,
449
- "normalized": false,
450
- "rstrip": false,
451
- "single_word": false,
452
- "special": true
453
- },
454
- "128056": {
455
- "content": "<|reserved_special_token_51|>",
456
- "lstrip": false,
457
- "normalized": false,
458
- "rstrip": false,
459
- "single_word": false,
460
- "special": true
461
- },
462
- "128057": {
463
- "content": "<|reserved_special_token_52|>",
464
- "lstrip": false,
465
- "normalized": false,
466
- "rstrip": false,
467
- "single_word": false,
468
- "special": true
469
- },
470
- "128058": {
471
- "content": "<|reserved_special_token_53|>",
472
- "lstrip": false,
473
- "normalized": false,
474
- "rstrip": false,
475
- "single_word": false,
476
- "special": true
477
- },
478
- "128059": {
479
- "content": "<|reserved_special_token_54|>",
480
- "lstrip": false,
481
- "normalized": false,
482
- "rstrip": false,
483
- "single_word": false,
484
- "special": true
485
- },
486
- "128060": {
487
- "content": "<|reserved_special_token_55|>",
488
- "lstrip": false,
489
- "normalized": false,
490
- "rstrip": false,
491
- "single_word": false,
492
- "special": true
493
- },
494
- "128061": {
495
- "content": "<|reserved_special_token_56|>",
496
- "lstrip": false,
497
- "normalized": false,
498
- "rstrip": false,
499
- "single_word": false,
500
- "special": true
501
- },
502
- "128062": {
503
- "content": "<|reserved_special_token_57|>",
504
- "lstrip": false,
505
- "normalized": false,
506
- "rstrip": false,
507
- "single_word": false,
508
- "special": true
509
- },
510
- "128063": {
511
- "content": "<|reserved_special_token_58|>",
512
- "lstrip": false,
513
- "normalized": false,
514
- "rstrip": false,
515
- "single_word": false,
516
- "special": true
517
- },
518
- "128064": {
519
- "content": "<|reserved_special_token_59|>",
520
- "lstrip": false,
521
- "normalized": false,
522
- "rstrip": false,
523
- "single_word": false,
524
- "special": true
525
- },
526
- "128065": {
527
- "content": "<|reserved_special_token_60|>",
528
- "lstrip": false,
529
- "normalized": false,
530
- "rstrip": false,
531
- "single_word": false,
532
- "special": true
533
- },
534
- "128066": {
535
- "content": "<|reserved_special_token_61|>",
536
- "lstrip": false,
537
- "normalized": false,
538
- "rstrip": false,
539
- "single_word": false,
540
- "special": true
541
- },
542
- "128067": {
543
- "content": "<|reserved_special_token_62|>",
544
- "lstrip": false,
545
- "normalized": false,
546
- "rstrip": false,
547
- "single_word": false,
548
- "special": true
549
- },
550
- "128068": {
551
- "content": "<|reserved_special_token_63|>",
552
- "lstrip": false,
553
- "normalized": false,
554
- "rstrip": false,
555
- "single_word": false,
556
- "special": true
557
- },
558
- "128069": {
559
- "content": "<|reserved_special_token_64|>",
560
- "lstrip": false,
561
- "normalized": false,
562
- "rstrip": false,
563
- "single_word": false,
564
- "special": true
565
- },
566
- "128070": {
567
- "content": "<|reserved_special_token_65|>",
568
- "lstrip": false,
569
- "normalized": false,
570
- "rstrip": false,
571
- "single_word": false,
572
- "special": true
573
- },
574
- "128071": {
575
- "content": "<|reserved_special_token_66|>",
576
- "lstrip": false,
577
- "normalized": false,
578
- "rstrip": false,
579
- "single_word": false,
580
- "special": true
581
- },
582
- "128072": {
583
- "content": "<|reserved_special_token_67|>",
584
- "lstrip": false,
585
- "normalized": false,
586
- "rstrip": false,
587
- "single_word": false,
588
- "special": true
589
- },
590
- "128073": {
591
- "content": "<|reserved_special_token_68|>",
592
- "lstrip": false,
593
- "normalized": false,
594
- "rstrip": false,
595
- "single_word": false,
596
- "special": true
597
- },
598
- "128074": {
599
- "content": "<|reserved_special_token_69|>",
600
- "lstrip": false,
601
- "normalized": false,
602
- "rstrip": false,
603
- "single_word": false,
604
- "special": true
605
- },
606
- "128075": {
607
- "content": "<|reserved_special_token_70|>",
608
- "lstrip": false,
609
- "normalized": false,
610
- "rstrip": false,
611
- "single_word": false,
612
- "special": true
613
- },
614
- "128076": {
615
- "content": "<|reserved_special_token_71|>",
616
- "lstrip": false,
617
- "normalized": false,
618
- "rstrip": false,
619
- "single_word": false,
620
- "special": true
621
- },
622
- "128077": {
623
- "content": "<|reserved_special_token_72|>",
624
- "lstrip": false,
625
- "normalized": false,
626
- "rstrip": false,
627
- "single_word": false,
628
- "special": true
629
- },
630
- "128078": {
631
- "content": "<|reserved_special_token_73|>",
632
- "lstrip": false,
633
- "normalized": false,
634
- "rstrip": false,
635
- "single_word": false,
636
- "special": true
637
- },
638
- "128079": {
639
- "content": "<|reserved_special_token_74|>",
640
- "lstrip": false,
641
- "normalized": false,
642
- "rstrip": false,
643
- "single_word": false,
644
- "special": true
645
- },
646
- "128080": {
647
- "content": "<|reserved_special_token_75|>",
648
- "lstrip": false,
649
- "normalized": false,
650
- "rstrip": false,
651
- "single_word": false,
652
- "special": true
653
- },
654
- "128081": {
655
- "content": "<|reserved_special_token_76|>",
656
- "lstrip": false,
657
- "normalized": false,
658
- "rstrip": false,
659
- "single_word": false,
660
- "special": true
661
- },
662
- "128082": {
663
- "content": "<|reserved_special_token_77|>",
664
- "lstrip": false,
665
- "normalized": false,
666
- "rstrip": false,
667
- "single_word": false,
668
- "special": true
669
- },
670
- "128083": {
671
- "content": "<|reserved_special_token_78|>",
672
- "lstrip": false,
673
- "normalized": false,
674
- "rstrip": false,
675
- "single_word": false,
676
- "special": true
677
- },
678
- "128084": {
679
- "content": "<|reserved_special_token_79|>",
680
- "lstrip": false,
681
- "normalized": false,
682
- "rstrip": false,
683
- "single_word": false,
684
- "special": true
685
- },
686
- "128085": {
687
- "content": "<|reserved_special_token_80|>",
688
- "lstrip": false,
689
- "normalized": false,
690
- "rstrip": false,
691
- "single_word": false,
692
- "special": true
693
- },
694
- "128086": {
695
- "content": "<|reserved_special_token_81|>",
696
- "lstrip": false,
697
- "normalized": false,
698
- "rstrip": false,
699
- "single_word": false,
700
- "special": true
701
- },
702
- "128087": {
703
- "content": "<|reserved_special_token_82|>",
704
- "lstrip": false,
705
- "normalized": false,
706
- "rstrip": false,
707
- "single_word": false,
708
- "special": true
709
- },
710
- "128088": {
711
- "content": "<|reserved_special_token_83|>",
712
- "lstrip": false,
713
- "normalized": false,
714
- "rstrip": false,
715
- "single_word": false,
716
- "special": true
717
- },
718
- "128089": {
719
- "content": "<|reserved_special_token_84|>",
720
- "lstrip": false,
721
- "normalized": false,
722
- "rstrip": false,
723
- "single_word": false,
724
- "special": true
725
- },
726
- "128090": {
727
- "content": "<|reserved_special_token_85|>",
728
- "lstrip": false,
729
- "normalized": false,
730
- "rstrip": false,
731
- "single_word": false,
732
- "special": true
733
- },
734
- "128091": {
735
- "content": "<|reserved_special_token_86|>",
736
- "lstrip": false,
737
- "normalized": false,
738
- "rstrip": false,
739
- "single_word": false,
740
- "special": true
741
- },
742
- "128092": {
743
- "content": "<|reserved_special_token_87|>",
744
- "lstrip": false,
745
- "normalized": false,
746
- "rstrip": false,
747
- "single_word": false,
748
- "special": true
749
- },
750
- "128093": {
751
- "content": "<|reserved_special_token_88|>",
752
- "lstrip": false,
753
- "normalized": false,
754
- "rstrip": false,
755
- "single_word": false,
756
- "special": true
757
- },
758
- "128094": {
759
- "content": "<|reserved_special_token_89|>",
760
- "lstrip": false,
761
- "normalized": false,
762
- "rstrip": false,
763
- "single_word": false,
764
- "special": true
765
- },
766
- "128095": {
767
- "content": "<|reserved_special_token_90|>",
768
- "lstrip": false,
769
- "normalized": false,
770
- "rstrip": false,
771
- "single_word": false,
772
- "special": true
773
- },
774
- "128096": {
775
- "content": "<|reserved_special_token_91|>",
776
- "lstrip": false,
777
- "normalized": false,
778
- "rstrip": false,
779
- "single_word": false,
780
- "special": true
781
- },
782
- "128097": {
783
- "content": "<|reserved_special_token_92|>",
784
- "lstrip": false,
785
- "normalized": false,
786
- "rstrip": false,
787
- "single_word": false,
788
- "special": true
789
- },
790
- "128098": {
791
- "content": "<|reserved_special_token_93|>",
792
- "lstrip": false,
793
- "normalized": false,
794
- "rstrip": false,
795
- "single_word": false,
796
- "special": true
797
- },
798
- "128099": {
799
- "content": "<|reserved_special_token_94|>",
800
- "lstrip": false,
801
- "normalized": false,
802
- "rstrip": false,
803
- "single_word": false,
804
- "special": true
805
- },
806
- "128100": {
807
- "content": "<|reserved_special_token_95|>",
808
- "lstrip": false,
809
- "normalized": false,
810
- "rstrip": false,
811
- "single_word": false,
812
- "special": true
813
- },
814
- "128101": {
815
- "content": "<|reserved_special_token_96|>",
816
- "lstrip": false,
817
- "normalized": false,
818
- "rstrip": false,
819
- "single_word": false,
820
- "special": true
821
- },
822
- "128102": {
823
- "content": "<|reserved_special_token_97|>",
824
- "lstrip": false,
825
- "normalized": false,
826
- "rstrip": false,
827
- "single_word": false,
828
- "special": true
829
- },
830
- "128103": {
831
- "content": "<|reserved_special_token_98|>",
832
- "lstrip": false,
833
- "normalized": false,
834
- "rstrip": false,
835
- "single_word": false,
836
- "special": true
837
- },
838
- "128104": {
839
- "content": "<|reserved_special_token_99|>",
840
- "lstrip": false,
841
- "normalized": false,
842
- "rstrip": false,
843
- "single_word": false,
844
- "special": true
845
- },
846
- "128105": {
847
- "content": "<|reserved_special_token_100|>",
848
- "lstrip": false,
849
- "normalized": false,
850
- "rstrip": false,
851
- "single_word": false,
852
- "special": true
853
- },
854
- "128106": {
855
- "content": "<|reserved_special_token_101|>",
856
- "lstrip": false,
857
- "normalized": false,
858
- "rstrip": false,
859
- "single_word": false,
860
- "special": true
861
- },
862
- "128107": {
863
- "content": "<|reserved_special_token_102|>",
864
- "lstrip": false,
865
- "normalized": false,
866
- "rstrip": false,
867
- "single_word": false,
868
- "special": true
869
- },
870
- "128108": {
871
- "content": "<|reserved_special_token_103|>",
872
- "lstrip": false,
873
- "normalized": false,
874
- "rstrip": false,
875
- "single_word": false,
876
- "special": true
877
- },
878
- "128109": {
879
- "content": "<|reserved_special_token_104|>",
880
- "lstrip": false,
881
- "normalized": false,
882
- "rstrip": false,
883
- "single_word": false,
884
- "special": true
885
- },
886
- "128110": {
887
- "content": "<|reserved_special_token_105|>",
888
- "lstrip": false,
889
- "normalized": false,
890
- "rstrip": false,
891
- "single_word": false,
892
- "special": true
893
- },
894
- "128111": {
895
- "content": "<|reserved_special_token_106|>",
896
- "lstrip": false,
897
- "normalized": false,
898
- "rstrip": false,
899
- "single_word": false,
900
- "special": true
901
- },
902
- "128112": {
903
- "content": "<|reserved_special_token_107|>",
904
- "lstrip": false,
905
- "normalized": false,
906
- "rstrip": false,
907
- "single_word": false,
908
- "special": true
909
- },
910
- "128113": {
911
- "content": "<|reserved_special_token_108|>",
912
- "lstrip": false,
913
- "normalized": false,
914
- "rstrip": false,
915
- "single_word": false,
916
- "special": true
917
- },
918
- "128114": {
919
- "content": "<|reserved_special_token_109|>",
920
- "lstrip": false,
921
- "normalized": false,
922
- "rstrip": false,
923
- "single_word": false,
924
- "special": true
925
- },
926
- "128115": {
927
- "content": "<|reserved_special_token_110|>",
928
- "lstrip": false,
929
- "normalized": false,
930
- "rstrip": false,
931
- "single_word": false,
932
- "special": true
933
- },
934
- "128116": {
935
- "content": "<|reserved_special_token_111|>",
936
- "lstrip": false,
937
- "normalized": false,
938
- "rstrip": false,
939
- "single_word": false,
940
- "special": true
941
- },
942
- "128117": {
943
- "content": "<|reserved_special_token_112|>",
944
- "lstrip": false,
945
- "normalized": false,
946
- "rstrip": false,
947
- "single_word": false,
948
- "special": true
949
- },
950
- "128118": {
951
- "content": "<|reserved_special_token_113|>",
952
- "lstrip": false,
953
- "normalized": false,
954
- "rstrip": false,
955
- "single_word": false,
956
- "special": true
957
- },
958
- "128119": {
959
- "content": "<|reserved_special_token_114|>",
960
- "lstrip": false,
961
- "normalized": false,
962
- "rstrip": false,
963
- "single_word": false,
964
- "special": true
965
- },
966
- "128120": {
967
- "content": "<|reserved_special_token_115|>",
968
- "lstrip": false,
969
- "normalized": false,
970
- "rstrip": false,
971
- "single_word": false,
972
- "special": true
973
- },
974
- "128121": {
975
- "content": "<|reserved_special_token_116|>",
976
- "lstrip": false,
977
- "normalized": false,
978
- "rstrip": false,
979
- "single_word": false,
980
- "special": true
981
- },
982
- "128122": {
983
- "content": "<|reserved_special_token_117|>",
984
- "lstrip": false,
985
- "normalized": false,
986
- "rstrip": false,
987
- "single_word": false,
988
- "special": true
989
- },
990
- "128123": {
991
- "content": "<|reserved_special_token_118|>",
992
- "lstrip": false,
993
- "normalized": false,
994
- "rstrip": false,
995
- "single_word": false,
996
- "special": true
997
- },
998
- "128124": {
999
- "content": "<|reserved_special_token_119|>",
1000
- "lstrip": false,
1001
- "normalized": false,
1002
- "rstrip": false,
1003
- "single_word": false,
1004
- "special": true
1005
- },
1006
- "128125": {
1007
- "content": "<|reserved_special_token_120|>",
1008
- "lstrip": false,
1009
- "normalized": false,
1010
- "rstrip": false,
1011
- "single_word": false,
1012
- "special": true
1013
- },
1014
- "128126": {
1015
- "content": "<|reserved_special_token_121|>",
1016
- "lstrip": false,
1017
- "normalized": false,
1018
- "rstrip": false,
1019
- "single_word": false,
1020
- "special": true
1021
- },
1022
- "128127": {
1023
- "content": "<|reserved_special_token_122|>",
1024
- "lstrip": false,
1025
- "normalized": false,
1026
- "rstrip": false,
1027
- "single_word": false,
1028
- "special": true
1029
- },
1030
- "128128": {
1031
- "content": "<|reserved_special_token_123|>",
1032
- "lstrip": false,
1033
- "normalized": false,
1034
- "rstrip": false,
1035
- "single_word": false,
1036
- "special": true
1037
- },
1038
- "128129": {
1039
- "content": "<|reserved_special_token_124|>",
1040
- "lstrip": false,
1041
- "normalized": false,
1042
- "rstrip": false,
1043
- "single_word": false,
1044
- "special": true
1045
- },
1046
- "128130": {
1047
- "content": "<|reserved_special_token_125|>",
1048
- "lstrip": false,
1049
- "normalized": false,
1050
- "rstrip": false,
1051
- "single_word": false,
1052
- "special": true
1053
- },
1054
- "128131": {
1055
- "content": "<|reserved_special_token_126|>",
1056
- "lstrip": false,
1057
- "normalized": false,
1058
- "rstrip": false,
1059
- "single_word": false,
1060
- "special": true
1061
- },
1062
- "128132": {
1063
- "content": "<|reserved_special_token_127|>",
1064
- "lstrip": false,
1065
- "normalized": false,
1066
- "rstrip": false,
1067
- "single_word": false,
1068
- "special": true
1069
- },
1070
- "128133": {
1071
- "content": "<|reserved_special_token_128|>",
1072
- "lstrip": false,
1073
- "normalized": false,
1074
- "rstrip": false,
1075
- "single_word": false,
1076
- "special": true
1077
- },
1078
- "128134": {
1079
- "content": "<|reserved_special_token_129|>",
1080
- "lstrip": false,
1081
- "normalized": false,
1082
- "rstrip": false,
1083
- "single_word": false,
1084
- "special": true
1085
- },
1086
- "128135": {
1087
- "content": "<|reserved_special_token_130|>",
1088
- "lstrip": false,
1089
- "normalized": false,
1090
- "rstrip": false,
1091
- "single_word": false,
1092
- "special": true
1093
- },
1094
- "128136": {
1095
- "content": "<|reserved_special_token_131|>",
1096
- "lstrip": false,
1097
- "normalized": false,
1098
- "rstrip": false,
1099
- "single_word": false,
1100
- "special": true
1101
- },
1102
- "128137": {
1103
- "content": "<|reserved_special_token_132|>",
1104
- "lstrip": false,
1105
- "normalized": false,
1106
- "rstrip": false,
1107
- "single_word": false,
1108
- "special": true
1109
- },
1110
- "128138": {
1111
- "content": "<|reserved_special_token_133|>",
1112
- "lstrip": false,
1113
- "normalized": false,
1114
- "rstrip": false,
1115
- "single_word": false,
1116
- "special": true
1117
- },
1118
- "128139": {
1119
- "content": "<|reserved_special_token_134|>",
1120
- "lstrip": false,
1121
- "normalized": false,
1122
- "rstrip": false,
1123
- "single_word": false,
1124
- "special": true
1125
- },
1126
- "128140": {
1127
- "content": "<|reserved_special_token_135|>",
1128
- "lstrip": false,
1129
- "normalized": false,
1130
- "rstrip": false,
1131
- "single_word": false,
1132
- "special": true
1133
- },
1134
- "128141": {
1135
- "content": "<|reserved_special_token_136|>",
1136
- "lstrip": false,
1137
- "normalized": false,
1138
- "rstrip": false,
1139
- "single_word": false,
1140
- "special": true
1141
- },
1142
- "128142": {
1143
- "content": "<|reserved_special_token_137|>",
1144
- "lstrip": false,
1145
- "normalized": false,
1146
- "rstrip": false,
1147
- "single_word": false,
1148
- "special": true
1149
- },
1150
- "128143": {
1151
- "content": "<|reserved_special_token_138|>",
1152
- "lstrip": false,
1153
- "normalized": false,
1154
- "rstrip": false,
1155
- "single_word": false,
1156
- "special": true
1157
- },
1158
- "128144": {
1159
- "content": "<|reserved_special_token_139|>",
1160
- "lstrip": false,
1161
- "normalized": false,
1162
- "rstrip": false,
1163
- "single_word": false,
1164
- "special": true
1165
- },
1166
- "128145": {
1167
- "content": "<|reserved_special_token_140|>",
1168
- "lstrip": false,
1169
- "normalized": false,
1170
- "rstrip": false,
1171
- "single_word": false,
1172
- "special": true
1173
- },
1174
- "128146": {
1175
- "content": "<|reserved_special_token_141|>",
1176
- "lstrip": false,
1177
- "normalized": false,
1178
- "rstrip": false,
1179
- "single_word": false,
1180
- "special": true
1181
- },
1182
- "128147": {
1183
- "content": "<|reserved_special_token_142|>",
1184
- "lstrip": false,
1185
- "normalized": false,
1186
- "rstrip": false,
1187
- "single_word": false,
1188
- "special": true
1189
- },
1190
- "128148": {
1191
- "content": "<|reserved_special_token_143|>",
1192
- "lstrip": false,
1193
- "normalized": false,
1194
- "rstrip": false,
1195
- "single_word": false,
1196
- "special": true
1197
- },
1198
- "128149": {
1199
- "content": "<|reserved_special_token_144|>",
1200
- "lstrip": false,
1201
- "normalized": false,
1202
- "rstrip": false,
1203
- "single_word": false,
1204
- "special": true
1205
- },
1206
- "128150": {
1207
- "content": "<|reserved_special_token_145|>",
1208
- "lstrip": false,
1209
- "normalized": false,
1210
- "rstrip": false,
1211
- "single_word": false,
1212
- "special": true
1213
- },
1214
- "128151": {
1215
- "content": "<|reserved_special_token_146|>",
1216
- "lstrip": false,
1217
- "normalized": false,
1218
- "rstrip": false,
1219
- "single_word": false,
1220
- "special": true
1221
- },
1222
- "128152": {
1223
- "content": "<|reserved_special_token_147|>",
1224
- "lstrip": false,
1225
- "normalized": false,
1226
- "rstrip": false,
1227
- "single_word": false,
1228
- "special": true
1229
- },
1230
- "128153": {
1231
- "content": "<|reserved_special_token_148|>",
1232
- "lstrip": false,
1233
- "normalized": false,
1234
- "rstrip": false,
1235
- "single_word": false,
1236
- "special": true
1237
- },
1238
- "128154": {
1239
- "content": "<|reserved_special_token_149|>",
1240
- "lstrip": false,
1241
- "normalized": false,
1242
- "rstrip": false,
1243
- "single_word": false,
1244
- "special": true
1245
- },
1246
- "128155": {
1247
- "content": "<|reserved_special_token_150|>",
1248
- "lstrip": false,
1249
- "normalized": false,
1250
- "rstrip": false,
1251
- "single_word": false,
1252
- "special": true
1253
- },
1254
- "128156": {
1255
- "content": "<|reserved_special_token_151|>",
1256
- "lstrip": false,
1257
- "normalized": false,
1258
- "rstrip": false,
1259
- "single_word": false,
1260
- "special": true
1261
- },
1262
- "128157": {
1263
- "content": "<|reserved_special_token_152|>",
1264
- "lstrip": false,
1265
- "normalized": false,
1266
- "rstrip": false,
1267
- "single_word": false,
1268
- "special": true
1269
- },
1270
- "128158": {
1271
- "content": "<|reserved_special_token_153|>",
1272
- "lstrip": false,
1273
- "normalized": false,
1274
- "rstrip": false,
1275
- "single_word": false,
1276
- "special": true
1277
- },
1278
- "128159": {
1279
- "content": "<|reserved_special_token_154|>",
1280
- "lstrip": false,
1281
- "normalized": false,
1282
- "rstrip": false,
1283
- "single_word": false,
1284
- "special": true
1285
- },
1286
- "128160": {
1287
- "content": "<|reserved_special_token_155|>",
1288
- "lstrip": false,
1289
- "normalized": false,
1290
- "rstrip": false,
1291
- "single_word": false,
1292
- "special": true
1293
- },
1294
- "128161": {
1295
- "content": "<|reserved_special_token_156|>",
1296
- "lstrip": false,
1297
- "normalized": false,
1298
- "rstrip": false,
1299
- "single_word": false,
1300
- "special": true
1301
- },
1302
- "128162": {
1303
- "content": "<|reserved_special_token_157|>",
1304
- "lstrip": false,
1305
- "normalized": false,
1306
- "rstrip": false,
1307
- "single_word": false,
1308
- "special": true
1309
- },
1310
- "128163": {
1311
- "content": "<|reserved_special_token_158|>",
1312
- "lstrip": false,
1313
- "normalized": false,
1314
- "rstrip": false,
1315
- "single_word": false,
1316
- "special": true
1317
- },
1318
- "128164": {
1319
- "content": "<|reserved_special_token_159|>",
1320
- "lstrip": false,
1321
- "normalized": false,
1322
- "rstrip": false,
1323
- "single_word": false,
1324
- "special": true
1325
- },
1326
- "128165": {
1327
- "content": "<|reserved_special_token_160|>",
1328
- "lstrip": false,
1329
- "normalized": false,
1330
- "rstrip": false,
1331
- "single_word": false,
1332
- "special": true
1333
- },
1334
- "128166": {
1335
- "content": "<|reserved_special_token_161|>",
1336
- "lstrip": false,
1337
- "normalized": false,
1338
- "rstrip": false,
1339
- "single_word": false,
1340
- "special": true
1341
- },
1342
- "128167": {
1343
- "content": "<|reserved_special_token_162|>",
1344
- "lstrip": false,
1345
- "normalized": false,
1346
- "rstrip": false,
1347
- "single_word": false,
1348
- "special": true
1349
- },
1350
- "128168": {
1351
- "content": "<|reserved_special_token_163|>",
1352
- "lstrip": false,
1353
- "normalized": false,
1354
- "rstrip": false,
1355
- "single_word": false,
1356
- "special": true
1357
- },
1358
- "128169": {
1359
- "content": "<|reserved_special_token_164|>",
1360
- "lstrip": false,
1361
- "normalized": false,
1362
- "rstrip": false,
1363
- "single_word": false,
1364
- "special": true
1365
- },
1366
- "128170": {
1367
- "content": "<|reserved_special_token_165|>",
1368
- "lstrip": false,
1369
- "normalized": false,
1370
- "rstrip": false,
1371
- "single_word": false,
1372
- "special": true
1373
- },
1374
- "128171": {
1375
- "content": "<|reserved_special_token_166|>",
1376
- "lstrip": false,
1377
- "normalized": false,
1378
- "rstrip": false,
1379
- "single_word": false,
1380
- "special": true
1381
- },
1382
- "128172": {
1383
- "content": "<|reserved_special_token_167|>",
1384
- "lstrip": false,
1385
- "normalized": false,
1386
- "rstrip": false,
1387
- "single_word": false,
1388
- "special": true
1389
- },
1390
- "128173": {
1391
- "content": "<|reserved_special_token_168|>",
1392
- "lstrip": false,
1393
- "normalized": false,
1394
- "rstrip": false,
1395
- "single_word": false,
1396
- "special": true
1397
- },
1398
- "128174": {
1399
- "content": "<|reserved_special_token_169|>",
1400
- "lstrip": false,
1401
- "normalized": false,
1402
- "rstrip": false,
1403
- "single_word": false,
1404
- "special": true
1405
- },
1406
- "128175": {
1407
- "content": "<|reserved_special_token_170|>",
1408
- "lstrip": false,
1409
- "normalized": false,
1410
- "rstrip": false,
1411
- "single_word": false,
1412
- "special": true
1413
- },
1414
- "128176": {
1415
- "content": "<|reserved_special_token_171|>",
1416
- "lstrip": false,
1417
- "normalized": false,
1418
- "rstrip": false,
1419
- "single_word": false,
1420
- "special": true
1421
- },
1422
- "128177": {
1423
- "content": "<|reserved_special_token_172|>",
1424
- "lstrip": false,
1425
- "normalized": false,
1426
- "rstrip": false,
1427
- "single_word": false,
1428
- "special": true
1429
- },
1430
- "128178": {
1431
- "content": "<|reserved_special_token_173|>",
1432
- "lstrip": false,
1433
- "normalized": false,
1434
- "rstrip": false,
1435
- "single_word": false,
1436
- "special": true
1437
- },
1438
- "128179": {
1439
- "content": "<|reserved_special_token_174|>",
1440
- "lstrip": false,
1441
- "normalized": false,
1442
- "rstrip": false,
1443
- "single_word": false,
1444
- "special": true
1445
- },
1446
- "128180": {
1447
- "content": "<|reserved_special_token_175|>",
1448
- "lstrip": false,
1449
- "normalized": false,
1450
- "rstrip": false,
1451
- "single_word": false,
1452
- "special": true
1453
- },
1454
- "128181": {
1455
- "content": "<|reserved_special_token_176|>",
1456
- "lstrip": false,
1457
- "normalized": false,
1458
- "rstrip": false,
1459
- "single_word": false,
1460
- "special": true
1461
- },
1462
- "128182": {
1463
- "content": "<|reserved_special_token_177|>",
1464
- "lstrip": false,
1465
- "normalized": false,
1466
- "rstrip": false,
1467
- "single_word": false,
1468
- "special": true
1469
- },
1470
- "128183": {
1471
- "content": "<|reserved_special_token_178|>",
1472
- "lstrip": false,
1473
- "normalized": false,
1474
- "rstrip": false,
1475
- "single_word": false,
1476
- "special": true
1477
- },
1478
- "128184": {
1479
- "content": "<|reserved_special_token_179|>",
1480
- "lstrip": false,
1481
- "normalized": false,
1482
- "rstrip": false,
1483
- "single_word": false,
1484
- "special": true
1485
- },
1486
- "128185": {
1487
- "content": "<|reserved_special_token_180|>",
1488
- "lstrip": false,
1489
- "normalized": false,
1490
- "rstrip": false,
1491
- "single_word": false,
1492
- "special": true
1493
- },
1494
- "128186": {
1495
- "content": "<|reserved_special_token_181|>",
1496
- "lstrip": false,
1497
- "normalized": false,
1498
- "rstrip": false,
1499
- "single_word": false,
1500
- "special": true
1501
- },
1502
- "128187": {
1503
- "content": "<|reserved_special_token_182|>",
1504
- "lstrip": false,
1505
- "normalized": false,
1506
- "rstrip": false,
1507
- "single_word": false,
1508
- "special": true
1509
- },
1510
- "128188": {
1511
- "content": "<|reserved_special_token_183|>",
1512
- "lstrip": false,
1513
- "normalized": false,
1514
- "rstrip": false,
1515
- "single_word": false,
1516
- "special": true
1517
- },
1518
- "128189": {
1519
- "content": "<|reserved_special_token_184|>",
1520
- "lstrip": false,
1521
- "normalized": false,
1522
- "rstrip": false,
1523
- "single_word": false,
1524
- "special": true
1525
- },
1526
- "128190": {
1527
- "content": "<|reserved_special_token_185|>",
1528
- "lstrip": false,
1529
- "normalized": false,
1530
- "rstrip": false,
1531
- "single_word": false,
1532
- "special": true
1533
- },
1534
- "128191": {
1535
- "content": "<|reserved_special_token_186|>",
1536
- "lstrip": false,
1537
- "normalized": false,
1538
- "rstrip": false,
1539
- "single_word": false,
1540
- "special": true
1541
- },
1542
- "128192": {
1543
- "content": "<|reserved_special_token_187|>",
1544
- "lstrip": false,
1545
- "normalized": false,
1546
- "rstrip": false,
1547
- "single_word": false,
1548
- "special": true
1549
- },
1550
- "128193": {
1551
- "content": "<|reserved_special_token_188|>",
1552
- "lstrip": false,
1553
- "normalized": false,
1554
- "rstrip": false,
1555
- "single_word": false,
1556
- "special": true
1557
- },
1558
- "128194": {
1559
- "content": "<|reserved_special_token_189|>",
1560
- "lstrip": false,
1561
- "normalized": false,
1562
- "rstrip": false,
1563
- "single_word": false,
1564
- "special": true
1565
- },
1566
- "128195": {
1567
- "content": "<|reserved_special_token_190|>",
1568
- "lstrip": false,
1569
- "normalized": false,
1570
- "rstrip": false,
1571
- "single_word": false,
1572
- "special": true
1573
- },
1574
- "128196": {
1575
- "content": "<|reserved_special_token_191|>",
1576
- "lstrip": false,
1577
- "normalized": false,
1578
- "rstrip": false,
1579
- "single_word": false,
1580
- "special": true
1581
- },
1582
- "128197": {
1583
- "content": "<|reserved_special_token_192|>",
1584
- "lstrip": false,
1585
- "normalized": false,
1586
- "rstrip": false,
1587
- "single_word": false,
1588
- "special": true
1589
- },
1590
- "128198": {
1591
- "content": "<|reserved_special_token_193|>",
1592
- "lstrip": false,
1593
- "normalized": false,
1594
- "rstrip": false,
1595
- "single_word": false,
1596
- "special": true
1597
- },
1598
- "128199": {
1599
- "content": "<|reserved_special_token_194|>",
1600
- "lstrip": false,
1601
- "normalized": false,
1602
- "rstrip": false,
1603
- "single_word": false,
1604
- "special": true
1605
- },
1606
- "128200": {
1607
- "content": "<|reserved_special_token_195|>",
1608
- "lstrip": false,
1609
- "normalized": false,
1610
- "rstrip": false,
1611
- "single_word": false,
1612
- "special": true
1613
- },
1614
- "128201": {
1615
- "content": "<|reserved_special_token_196|>",
1616
- "lstrip": false,
1617
- "normalized": false,
1618
- "rstrip": false,
1619
- "single_word": false,
1620
- "special": true
1621
- },
1622
- "128202": {
1623
- "content": "<|reserved_special_token_197|>",
1624
- "lstrip": false,
1625
- "normalized": false,
1626
- "rstrip": false,
1627
- "single_word": false,
1628
- "special": true
1629
- },
1630
- "128203": {
1631
- "content": "<|reserved_special_token_198|>",
1632
- "lstrip": false,
1633
- "normalized": false,
1634
- "rstrip": false,
1635
- "single_word": false,
1636
- "special": true
1637
- },
1638
- "128204": {
1639
- "content": "<|reserved_special_token_199|>",
1640
- "lstrip": false,
1641
- "normalized": false,
1642
- "rstrip": false,
1643
- "single_word": false,
1644
- "special": true
1645
- },
1646
- "128205": {
1647
- "content": "<|reserved_special_token_200|>",
1648
- "lstrip": false,
1649
- "normalized": false,
1650
- "rstrip": false,
1651
- "single_word": false,
1652
- "special": true
1653
- },
1654
- "128206": {
1655
- "content": "<|reserved_special_token_201|>",
1656
- "lstrip": false,
1657
- "normalized": false,
1658
- "rstrip": false,
1659
- "single_word": false,
1660
- "special": true
1661
- },
1662
- "128207": {
1663
- "content": "<|reserved_special_token_202|>",
1664
- "lstrip": false,
1665
- "normalized": false,
1666
- "rstrip": false,
1667
- "single_word": false,
1668
- "special": true
1669
- },
1670
- "128208": {
1671
- "content": "<|reserved_special_token_203|>",
1672
- "lstrip": false,
1673
- "normalized": false,
1674
- "rstrip": false,
1675
- "single_word": false,
1676
- "special": true
1677
- },
1678
- "128209": {
1679
- "content": "<|reserved_special_token_204|>",
1680
- "lstrip": false,
1681
- "normalized": false,
1682
- "rstrip": false,
1683
- "single_word": false,
1684
- "special": true
1685
- },
1686
- "128210": {
1687
- "content": "<|reserved_special_token_205|>",
1688
- "lstrip": false,
1689
- "normalized": false,
1690
- "rstrip": false,
1691
- "single_word": false,
1692
- "special": true
1693
- },
1694
- "128211": {
1695
- "content": "<|reserved_special_token_206|>",
1696
- "lstrip": false,
1697
- "normalized": false,
1698
- "rstrip": false,
1699
- "single_word": false,
1700
- "special": true
1701
- },
1702
- "128212": {
1703
- "content": "<|reserved_special_token_207|>",
1704
- "lstrip": false,
1705
- "normalized": false,
1706
- "rstrip": false,
1707
- "single_word": false,
1708
- "special": true
1709
- },
1710
- "128213": {
1711
- "content": "<|reserved_special_token_208|>",
1712
- "lstrip": false,
1713
- "normalized": false,
1714
- "rstrip": false,
1715
- "single_word": false,
1716
- "special": true
1717
- },
1718
- "128214": {
1719
- "content": "<|reserved_special_token_209|>",
1720
- "lstrip": false,
1721
- "normalized": false,
1722
- "rstrip": false,
1723
- "single_word": false,
1724
- "special": true
1725
- },
1726
- "128215": {
1727
- "content": "<|reserved_special_token_210|>",
1728
- "lstrip": false,
1729
- "normalized": false,
1730
- "rstrip": false,
1731
- "single_word": false,
1732
- "special": true
1733
- },
1734
- "128216": {
1735
- "content": "<|reserved_special_token_211|>",
1736
- "lstrip": false,
1737
- "normalized": false,
1738
- "rstrip": false,
1739
- "single_word": false,
1740
- "special": true
1741
- },
1742
- "128217": {
1743
- "content": "<|reserved_special_token_212|>",
1744
- "lstrip": false,
1745
- "normalized": false,
1746
- "rstrip": false,
1747
- "single_word": false,
1748
- "special": true
1749
- },
1750
- "128218": {
1751
- "content": "<|reserved_special_token_213|>",
1752
- "lstrip": false,
1753
- "normalized": false,
1754
- "rstrip": false,
1755
- "single_word": false,
1756
- "special": true
1757
- },
1758
- "128219": {
1759
- "content": "<|reserved_special_token_214|>",
1760
- "lstrip": false,
1761
- "normalized": false,
1762
- "rstrip": false,
1763
- "single_word": false,
1764
- "special": true
1765
- },
1766
- "128220": {
1767
- "content": "<|reserved_special_token_215|>",
1768
- "lstrip": false,
1769
- "normalized": false,
1770
- "rstrip": false,
1771
- "single_word": false,
1772
- "special": true
1773
- },
1774
- "128221": {
1775
- "content": "<|reserved_special_token_216|>",
1776
- "lstrip": false,
1777
- "normalized": false,
1778
- "rstrip": false,
1779
- "single_word": false,
1780
- "special": true
1781
- },
1782
- "128222": {
1783
- "content": "<|reserved_special_token_217|>",
1784
- "lstrip": false,
1785
- "normalized": false,
1786
- "rstrip": false,
1787
- "single_word": false,
1788
- "special": true
1789
- },
1790
- "128223": {
1791
- "content": "<|reserved_special_token_218|>",
1792
- "lstrip": false,
1793
- "normalized": false,
1794
- "rstrip": false,
1795
- "single_word": false,
1796
- "special": true
1797
- },
1798
- "128224": {
1799
- "content": "<|reserved_special_token_219|>",
1800
- "lstrip": false,
1801
- "normalized": false,
1802
- "rstrip": false,
1803
- "single_word": false,
1804
- "special": true
1805
- },
1806
- "128225": {
1807
- "content": "<|reserved_special_token_220|>",
1808
- "lstrip": false,
1809
- "normalized": false,
1810
- "rstrip": false,
1811
- "single_word": false,
1812
- "special": true
1813
- },
1814
- "128226": {
1815
- "content": "<|reserved_special_token_221|>",
1816
- "lstrip": false,
1817
- "normalized": false,
1818
- "rstrip": false,
1819
- "single_word": false,
1820
- "special": true
1821
- },
1822
- "128227": {
1823
- "content": "<|reserved_special_token_222|>",
1824
- "lstrip": false,
1825
- "normalized": false,
1826
- "rstrip": false,
1827
- "single_word": false,
1828
- "special": true
1829
- },
1830
- "128228": {
1831
- "content": "<|reserved_special_token_223|>",
1832
- "lstrip": false,
1833
- "normalized": false,
1834
- "rstrip": false,
1835
- "single_word": false,
1836
- "special": true
1837
- },
1838
- "128229": {
1839
- "content": "<|reserved_special_token_224|>",
1840
- "lstrip": false,
1841
- "normalized": false,
1842
- "rstrip": false,
1843
- "single_word": false,
1844
- "special": true
1845
- },
1846
- "128230": {
1847
- "content": "<|reserved_special_token_225|>",
1848
- "lstrip": false,
1849
- "normalized": false,
1850
- "rstrip": false,
1851
- "single_word": false,
1852
- "special": true
1853
- },
1854
- "128231": {
1855
- "content": "<|reserved_special_token_226|>",
1856
- "lstrip": false,
1857
- "normalized": false,
1858
- "rstrip": false,
1859
- "single_word": false,
1860
- "special": true
1861
- },
1862
- "128232": {
1863
- "content": "<|reserved_special_token_227|>",
1864
- "lstrip": false,
1865
- "normalized": false,
1866
- "rstrip": false,
1867
- "single_word": false,
1868
- "special": true
1869
- },
1870
- "128233": {
1871
- "content": "<|reserved_special_token_228|>",
1872
- "lstrip": false,
1873
- "normalized": false,
1874
- "rstrip": false,
1875
- "single_word": false,
1876
- "special": true
1877
- },
1878
- "128234": {
1879
- "content": "<|reserved_special_token_229|>",
1880
- "lstrip": false,
1881
- "normalized": false,
1882
- "rstrip": false,
1883
- "single_word": false,
1884
- "special": true
1885
- },
1886
- "128235": {
1887
- "content": "<|reserved_special_token_230|>",
1888
- "lstrip": false,
1889
- "normalized": false,
1890
- "rstrip": false,
1891
- "single_word": false,
1892
- "special": true
1893
- },
1894
- "128236": {
1895
- "content": "<|reserved_special_token_231|>",
1896
- "lstrip": false,
1897
- "normalized": false,
1898
- "rstrip": false,
1899
- "single_word": false,
1900
- "special": true
1901
- },
1902
- "128237": {
1903
- "content": "<|reserved_special_token_232|>",
1904
- "lstrip": false,
1905
- "normalized": false,
1906
- "rstrip": false,
1907
- "single_word": false,
1908
- "special": true
1909
- },
1910
- "128238": {
1911
- "content": "<|reserved_special_token_233|>",
1912
- "lstrip": false,
1913
- "normalized": false,
1914
- "rstrip": false,
1915
- "single_word": false,
1916
- "special": true
1917
- },
1918
- "128239": {
1919
- "content": "<|reserved_special_token_234|>",
1920
- "lstrip": false,
1921
- "normalized": false,
1922
- "rstrip": false,
1923
- "single_word": false,
1924
- "special": true
1925
- },
1926
- "128240": {
1927
- "content": "<|reserved_special_token_235|>",
1928
- "lstrip": false,
1929
- "normalized": false,
1930
- "rstrip": false,
1931
- "single_word": false,
1932
- "special": true
1933
- },
1934
- "128241": {
1935
- "content": "<|reserved_special_token_236|>",
1936
- "lstrip": false,
1937
- "normalized": false,
1938
- "rstrip": false,
1939
- "single_word": false,
1940
- "special": true
1941
- },
1942
- "128242": {
1943
- "content": "<|reserved_special_token_237|>",
1944
- "lstrip": false,
1945
- "normalized": false,
1946
- "rstrip": false,
1947
- "single_word": false,
1948
- "special": true
1949
- },
1950
- "128243": {
1951
- "content": "<|reserved_special_token_238|>",
1952
- "lstrip": false,
1953
- "normalized": false,
1954
- "rstrip": false,
1955
- "single_word": false,
1956
- "special": true
1957
- },
1958
- "128244": {
1959
- "content": "<|reserved_special_token_239|>",
1960
- "lstrip": false,
1961
- "normalized": false,
1962
- "rstrip": false,
1963
- "single_word": false,
1964
- "special": true
1965
- },
1966
- "128245": {
1967
- "content": "<|reserved_special_token_240|>",
1968
- "lstrip": false,
1969
- "normalized": false,
1970
- "rstrip": false,
1971
- "single_word": false,
1972
- "special": true
1973
- },
1974
- "128246": {
1975
- "content": "<|reserved_special_token_241|>",
1976
- "lstrip": false,
1977
- "normalized": false,
1978
- "rstrip": false,
1979
- "single_word": false,
1980
- "special": true
1981
- },
1982
- "128247": {
1983
- "content": "<|reserved_special_token_242|>",
1984
- "lstrip": false,
1985
- "normalized": false,
1986
- "rstrip": false,
1987
- "single_word": false,
1988
- "special": true
1989
- },
1990
- "128248": {
1991
- "content": "<|reserved_special_token_243|>",
1992
- "lstrip": false,
1993
- "normalized": false,
1994
- "rstrip": false,
1995
- "single_word": false,
1996
- "special": true
1997
- },
1998
- "128249": {
1999
- "content": "<|reserved_special_token_244|>",
2000
- "lstrip": false,
2001
- "normalized": false,
2002
- "rstrip": false,
2003
- "single_word": false,
2004
- "special": true
2005
- },
2006
- "128250": {
2007
- "content": "<|reserved_special_token_245|>",
2008
- "lstrip": false,
2009
- "normalized": false,
2010
- "rstrip": false,
2011
- "single_word": false,
2012
- "special": true
2013
- },
2014
- "128251": {
2015
- "content": "<|reserved_special_token_246|>",
2016
- "lstrip": false,
2017
- "normalized": false,
2018
- "rstrip": false,
2019
- "single_word": false,
2020
- "special": true
2021
- },
2022
- "128252": {
2023
- "content": "<|reserved_special_token_247|>",
2024
- "lstrip": false,
2025
- "normalized": false,
2026
- "rstrip": false,
2027
- "single_word": false,
2028
- "special": true
2029
- },
2030
- "128253": {
2031
- "content": "<|reserved_special_token_248|>",
2032
- "lstrip": false,
2033
- "normalized": false,
2034
- "rstrip": false,
2035
- "single_word": false,
2036
- "special": true
2037
- },
2038
- "128254": {
2039
- "content": "<|reserved_special_token_249|>",
2040
- "lstrip": false,
2041
- "normalized": false,
2042
- "rstrip": false,
2043
- "single_word": false,
2044
- "special": true
2045
- },
2046
- "128255": {
2047
- "content": "<|reserved_special_token_250|>",
2048
- "lstrip": false,
2049
- "normalized": false,
2050
- "rstrip": false,
2051
- "single_word": false,
2052
- "special": true
2053
- },
2054
- "128256": {
2055
- "content": "<image>",
2056
- "lstrip": false,
2057
- "normalized": false,
2058
- "rstrip": false,
2059
- "single_word": false,
2060
- "special": true
2061
- },
2062
- "128257": {
2063
- "content": "<|pad|>",
2064
- "lstrip": false,
2065
- "normalized": false,
2066
- "rstrip": false,
2067
- "single_word": false,
2068
- "special": true
2069
- },
2070
- "128258": {
2071
- "content": "<unk>",
2072
- "lstrip": false,
2073
- "normalized": false,
2074
- "rstrip": false,
2075
- "single_word": false,
2076
- "special": true
2077
- }
2078
- },
2079
- "additional_special_tokens": [
2080
- "<image>",
2081
- "<|pad|>"
2082
- ],
2083
- "bos_token": "<|begin_of_text|>",
2084
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2085
- "clean_up_tokenization_spaces": true,
2086
- "eos_token": "<|end_of_text|>",
2087
- "legacy": true,
2088
- "model_input_names": [
2089
- "input_ids",
2090
- "attention_mask"
2091
- ],
2092
- "model_max_length": 1000000000000000019884624838656,
2093
- "processor_class": "MLlavaProcessor",
2094
- "tokenizer_class": "LlamaTokenizer",
2095
- "unk_token": "<unk>",
2096
- "use_default_system_prompt": false
2097
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-4578/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-4578/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:73a84c0e77975b5854f85d575961e1fb85c1e7bd1e24ab06515d493f7afb9000
3
- size 6648
 
 
 
 
checkpoint-4578/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)