Hugging Face's logo

DeeptraceReward
/
RewardModel

Safetensors
videollama3_qwen2
custom_code
Model card Files
xet
Community
1
Xingyu Fu commited on
Commit
289bb98
·
1 Parent(s): 14f85e6

First model version

Browse files
Files changed (20) hide show
  1. added_tokens.json +27 -0
  2. config.json +126 -0
  3. generation_config.json +6 -0
  4. latest +1 -0
  5. merges.txt +0 -0
  6. model-00001-of-00004.safetensors +3 -0
  7. model-00002-of-00004.safetensors +3 -0
  8. model-00003-of-00004.safetensors +3 -0
  9. model-00004-of-00004.safetensors +3 -0
  10. model.safetensors.index.json +786 -0
  11. rng_state_0.pth +3 -0
  12. rng_state_1.pth +3 -0
  13. rng_state_2.pth +3 -0
  14. scheduler.pt +3 -0
  15. special_tokens_map.json +31 -0
  16. tokenizer_config.json +236 -0
  17. trainer_state.json +740 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
  20. zero_to_fp32.py +674 -0
added_tokens.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<image>": 151665,
4
+ "<tool_call>": 151657,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|stream_end|>": 151667,
22
+ "<|stream_start|>": 151666,
23
+ "<|video_pad|>": 151656,
24
+ "<|vision_end|>": 151653,
25
+ "<|vision_pad|>": 151654,
26
+ "<|vision_start|>": 151652
27
+ }
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/gpfs/xf0532/deepfake/VideoLLaMA3/weights/videollama3_7b_local",
3
+ "architectures": [
4
+ "Videollama3Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "DAMO-NLP-SG/VideoLLaMA3-7B--configuration_videollama3.Videollama3Qwen2Config",
9
+ "AutoModelForCausalLM": "DAMO-NLP-SG/VideoLLaMA3-7B--modeling_videollama3.Videollama3Qwen2ForCausalLM"
10
+ },
11
+ "bos_token_id": 151643,
12
+ "eos_token_id": 151645,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "image_aspect_ratio": "square",
16
+ "image_size": -1,
17
+ "image_token_index": 151665,
18
+ "image_token_length": 1,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 18944,
21
+ "is_alignment": false,
22
+ "llm_lr": 1e-05,
23
+ "max_frames": 60,
24
+ "max_position_embeddings": 32768,
25
+ "max_window_layers": 28,
26
+ "mm_hidden_size": 1152,
27
+ "mm_projector_lr": 1e-05,
28
+ "mm_projector_type": "mlp2x_gelu",
29
+ "mm_vision_encoder": "/scratch/gpfs/xf0532/deepfake/VideoLLaMA3/SigLIP-NaViT",
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -1,
32
+ "model_type": "videollama3_qwen2",
33
+ "num_attention_heads": 28,
34
+ "num_hidden_layers": 28,
35
+ "num_key_value_heads": 4,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_scaling": null,
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "tokenizer_model_max_length": 16384,
42
+ "tokenizer_padding_side": "right",
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.46.3",
45
+ "use_cache": false,
46
+ "use_flash_loss": false,
47
+ "use_mm_proj": true,
48
+ "use_sliding_window": false,
49
+ "use_token_compression": true,
50
+ "vision_encoder": "/scratch/gpfs/xf0532/deepfake/VideoLLaMA3/SigLIP-NaViT",
51
+ "vision_encoder_config": {
52
+ "_attn_implementation_autoset": false,
53
+ "_name_or_path": "",
54
+ "add_cross_attention": false,
55
+ "architectures": null,
56
+ "attention_dropout": 0.0,
57
+ "bad_words_ids": null,
58
+ "begin_suppress_tokens": null,
59
+ "bos_token_id": null,
60
+ "chunk_size_feed_forward": 0,
61
+ "cross_attention_hidden_size": null,
62
+ "decoder_start_token_id": null,
63
+ "diversity_penalty": 0.0,
64
+ "do_sample": false,
65
+ "early_stopping": false,
66
+ "encoder_no_repeat_ngram_size": 0,
67
+ "eos_token_id": null,
68
+ "exponential_decay_length_penalty": null,
69
+ "finetuning_task": null,
70
+ "forced_bos_token_id": null,
71
+ "forced_eos_token_id": null,
72
+ "hidden_act": "gelu_pytorch_tanh",
73
+ "hidden_size": 1152,
74
+ "id2label": {
75
+ "0": "LABEL_0",
76
+ "1": "LABEL_1"
77
+ },
78
+ "intermediate_size": 4304,
79
+ "is_decoder": false,
80
+ "is_encoder_decoder": false,
81
+ "label2id": {
82
+ "LABEL_0": 0,
83
+ "LABEL_1": 1
84
+ },
85
+ "layer_norm_eps": 1e-06,
86
+ "length_penalty": 1.0,
87
+ "max_length": 20,
88
+ "min_length": 0,
89
+ "model_type": "videollama3_vision_encoder",
90
+ "no_repeat_ngram_size": 0,
91
+ "num_attention_heads": 16,
92
+ "num_beam_groups": 1,
93
+ "num_beams": 1,
94
+ "num_channels": 3,
95
+ "num_hidden_layers": 27,
96
+ "num_return_sequences": 1,
97
+ "output_attentions": false,
98
+ "output_hidden_states": false,
99
+ "output_scores": false,
100
+ "pad_token_id": null,
101
+ "patch_size": 14,
102
+ "prefix": null,
103
+ "problem_type": null,
104
+ "pruned_heads": {},
105
+ "remove_invalid_values": false,
106
+ "repetition_penalty": 1.0,
107
+ "return_dict": true,
108
+ "return_dict_in_generate": false,
109
+ "sep_token_id": null,
110
+ "suppress_tokens": null,
111
+ "task_specific_params": null,
112
+ "temperature": 1.0,
113
+ "tf_legacy_loss": false,
114
+ "tie_encoder_decoder": false,
115
+ "tie_word_embeddings": true,
116
+ "tokenizer_class": null,
117
+ "top_k": 50,
118
+ "top_p": 1.0,
119
+ "torch_dtype": null,
120
+ "torchscript": false,
121
+ "typical_p": 1.0,
122
+ "use_bfloat16": false
123
+ },
124
+ "vision_encoder_lr": 2e-06,
125
+ "vocab_size": 152064
126
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.46.3"
6
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step101
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f520085f7ff1ffd19eb0ca6ee4d08518c27804a2bbd62484d67cb5f391a720c
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21744419f4ca67857d3ead7597c8fff89e712c5097ff9b0338d94f7a422e2d92
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd844b533defce1ac945778c91707e90a17211be4b892777c013361df20a0547
3
+ size 4992888976
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09096f9290fd2a390adaae69546b7ddec6b326221d1dc4bedf98594b5ffe7e9d
3
+ size 1286293008
model.safetensors.index.json ADDED
@@ -0,0 +1,786 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16089489888
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.mm_projector.readout.0.bias": "model-00004-of-00004.safetensors",
345
+ "model.mm_projector.readout.0.weight": "model-00004-of-00004.safetensors",
346
+ "model.mm_projector.readout.2.bias": "model-00004-of-00004.safetensors",
347
+ "model.mm_projector.readout.2.weight": "model-00004-of-00004.safetensors",
348
+ "model.norm.weight": "model-00003-of-00004.safetensors",
349
+ "model.vision_encoder.vision_encoder.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
350
+ "model.vision_encoder.vision_encoder.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
351
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
352
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
353
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
354
+ "model.vision_encoder.vision_encoder.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
355
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
356
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
357
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
358
+ "model.vision_encoder.vision_encoder.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
359
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
360
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
361
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
362
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
363
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
364
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
365
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
366
+ "model.vision_encoder.vision_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
367
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
368
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
369
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
370
+ "model.vision_encoder.vision_encoder.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
371
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
372
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
373
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
374
+ "model.vision_encoder.vision_encoder.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
375
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
376
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
377
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
378
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
379
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
380
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
381
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
382
+ "model.vision_encoder.vision_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
383
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
384
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
385
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
386
+ "model.vision_encoder.vision_encoder.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
387
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
388
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
389
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
390
+ "model.vision_encoder.vision_encoder.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
391
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
392
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
393
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
394
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
395
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
396
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
397
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
398
+ "model.vision_encoder.vision_encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
399
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
400
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
401
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
402
+ "model.vision_encoder.vision_encoder.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
403
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
404
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
405
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
406
+ "model.vision_encoder.vision_encoder.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
407
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
408
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
409
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
410
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
411
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
412
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
413
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
414
+ "model.vision_encoder.vision_encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
415
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
416
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
417
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
418
+ "model.vision_encoder.vision_encoder.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
419
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
420
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
421
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
422
+ "model.vision_encoder.vision_encoder.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
423
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
424
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
425
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
426
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
427
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
428
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
429
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
430
+ "model.vision_encoder.vision_encoder.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
431
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
432
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
433
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
434
+ "model.vision_encoder.vision_encoder.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
435
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
436
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
437
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
438
+ "model.vision_encoder.vision_encoder.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
439
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
440
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
441
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
442
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
443
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
444
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
445
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
446
+ "model.vision_encoder.vision_encoder.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
447
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
448
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
449
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
450
+ "model.vision_encoder.vision_encoder.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
451
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
452
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
453
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
454
+ "model.vision_encoder.vision_encoder.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
455
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
456
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
457
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
458
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
459
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
460
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
461
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
462
+ "model.vision_encoder.vision_encoder.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
463
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
464
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
465
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
466
+ "model.vision_encoder.vision_encoder.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
467
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
468
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
469
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
470
+ "model.vision_encoder.vision_encoder.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
471
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
472
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
473
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
474
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
475
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
476
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
477
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
478
+ "model.vision_encoder.vision_encoder.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
479
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
480
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
481
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
482
+ "model.vision_encoder.vision_encoder.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
483
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
484
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
485
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
486
+ "model.vision_encoder.vision_encoder.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
487
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
488
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
489
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
490
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
491
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
492
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
493
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
494
+ "model.vision_encoder.vision_encoder.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
495
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
496
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
497
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
498
+ "model.vision_encoder.vision_encoder.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
499
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
500
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
501
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
502
+ "model.vision_encoder.vision_encoder.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
503
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
504
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
505
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
506
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
507
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
508
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
509
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
510
+ "model.vision_encoder.vision_encoder.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
511
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
512
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
513
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
514
+ "model.vision_encoder.vision_encoder.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
515
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
516
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
517
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
518
+ "model.vision_encoder.vision_encoder.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
519
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
520
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
521
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
522
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
523
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
524
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
525
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
526
+ "model.vision_encoder.vision_encoder.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
527
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
528
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
529
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
530
+ "model.vision_encoder.vision_encoder.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
531
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
532
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
533
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
534
+ "model.vision_encoder.vision_encoder.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
535
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
536
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
537
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
538
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
539
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
540
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
541
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
542
+ "model.vision_encoder.vision_encoder.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
543
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
544
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
545
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
546
+ "model.vision_encoder.vision_encoder.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
547
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
548
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
549
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
550
+ "model.vision_encoder.vision_encoder.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
551
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
552
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
553
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
554
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
555
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
556
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
557
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
558
+ "model.vision_encoder.vision_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
559
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
560
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
561
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
562
+ "model.vision_encoder.vision_encoder.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
563
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
564
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
565
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
566
+ "model.vision_encoder.vision_encoder.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
567
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
568
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
569
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
570
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
571
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
572
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
573
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
574
+ "model.vision_encoder.vision_encoder.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
575
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
576
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
577
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
578
+ "model.vision_encoder.vision_encoder.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
579
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
580
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
581
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
582
+ "model.vision_encoder.vision_encoder.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
583
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
584
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
585
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
586
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
587
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
588
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
589
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
590
+ "model.vision_encoder.vision_encoder.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
591
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
592
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
593
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
594
+ "model.vision_encoder.vision_encoder.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
595
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
596
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
597
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
598
+ "model.vision_encoder.vision_encoder.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
599
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
600
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
601
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
602
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
603
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
604
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
605
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
606
+ "model.vision_encoder.vision_encoder.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
607
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
608
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
609
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
610
+ "model.vision_encoder.vision_encoder.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
611
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
612
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
613
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
614
+ "model.vision_encoder.vision_encoder.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
615
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
616
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
617
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
618
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
619
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
620
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
621
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
622
+ "model.vision_encoder.vision_encoder.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
623
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
624
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
625
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
626
+ "model.vision_encoder.vision_encoder.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
627
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
628
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
629
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
630
+ "model.vision_encoder.vision_encoder.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
631
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
632
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
633
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
634
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
635
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
636
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
637
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
638
+ "model.vision_encoder.vision_encoder.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
639
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
640
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
641
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
642
+ "model.vision_encoder.vision_encoder.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
643
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
644
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
645
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
646
+ "model.vision_encoder.vision_encoder.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
647
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
648
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
649
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
650
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
651
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
652
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
653
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
654
+ "model.vision_encoder.vision_encoder.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
655
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm1.bias": "model-00004-of-00004.safetensors",
656
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm1.weight": "model-00004-of-00004.safetensors",
657
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm2.bias": "model-00004-of-00004.safetensors",
658
+ "model.vision_encoder.vision_encoder.encoder.layers.26.layer_norm2.weight": "model-00004-of-00004.safetensors",
659
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc1.bias": "model-00004-of-00004.safetensors",
660
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc1.weight": "model-00004-of-00004.safetensors",
661
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc2.bias": "model-00004-of-00004.safetensors",
662
+ "model.vision_encoder.vision_encoder.encoder.layers.26.mlp.fc2.weight": "model-00004-of-00004.safetensors",
663
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
664
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
665
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
666
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
667
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
668
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
669
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
670
+ "model.vision_encoder.vision_encoder.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
671
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
672
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
673
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
674
+ "model.vision_encoder.vision_encoder.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
675
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
676
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
677
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
678
+ "model.vision_encoder.vision_encoder.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
679
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
680
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
681
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
682
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
683
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
684
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
685
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
686
+ "model.vision_encoder.vision_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
687
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
688
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
689
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
690
+ "model.vision_encoder.vision_encoder.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
691
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
692
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
693
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
694
+ "model.vision_encoder.vision_encoder.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
695
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
696
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
697
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
698
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
699
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
700
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
701
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
702
+ "model.vision_encoder.vision_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
703
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
704
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
705
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
706
+ "model.vision_encoder.vision_encoder.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
707
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
708
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
709
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
710
+ "model.vision_encoder.vision_encoder.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
711
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
712
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
713
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
714
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
715
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
716
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
717
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
718
+ "model.vision_encoder.vision_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
719
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
720
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
721
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
722
+ "model.vision_encoder.vision_encoder.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
723
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
724
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
725
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
726
+ "model.vision_encoder.vision_encoder.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
727
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
728
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
729
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
730
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
731
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
732
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
733
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
734
+ "model.vision_encoder.vision_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
735
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
736
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
737
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
738
+ "model.vision_encoder.vision_encoder.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
739
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
740
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
741
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
742
+ "model.vision_encoder.vision_encoder.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
743
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
744
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
745
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
746
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
747
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
748
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
749
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
750
+ "model.vision_encoder.vision_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
751
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
752
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
753
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
754
+ "model.vision_encoder.vision_encoder.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
755
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
756
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
757
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
758
+ "model.vision_encoder.vision_encoder.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
759
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
760
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
761
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
762
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
763
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
764
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
765
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
766
+ "model.vision_encoder.vision_encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
767
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
768
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
769
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
770
+ "model.vision_encoder.vision_encoder.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
771
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
772
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
773
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
774
+ "model.vision_encoder.vision_encoder.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
775
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
776
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
777
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
778
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
779
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
780
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
781
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
782
+ "model.vision_encoder.vision_encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
783
+ "model.vision_encoder.vision_encoder.post_layernorm.bias": "model-00004-of-00004.safetensors",
784
+ "model.vision_encoder.vision_encoder.post_layernorm.weight": "model-00004-of-00004.safetensors"
785
+ }
786
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ad2cbc3c7a0fefa416ca212a3ca0c765342dd508d3b01b19c9bdea93628432
3
+ size 14768
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9903702cd62a564aeefa5a7e25e7880f9da928b6f8206920658a1bffb56fd4d
3
+ size 14768
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e2a0709246422023102bef738c8b868479d2bb14ff3437e9da4185d107bb40
3
+ size 14768
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2147b7ebacbd0ca1aaa3267479e04f5d5114f86ff52594e9dff08264aafcbb2
3
+ size 1128
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|stream_start|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|stream_end|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ }
205
+ },
206
+ "additional_special_tokens": [
207
+ "<|im_start|>",
208
+ "<|im_end|>",
209
+ "<|object_ref_start|>",
210
+ "<|object_ref_end|>",
211
+ "<|box_start|>",
212
+ "<|box_end|>",
213
+ "<|quad_start|>",
214
+ "<|quad_end|>",
215
+ "<|vision_start|>",
216
+ "<|vision_end|>",
217
+ "<|vision_pad|>",
218
+ "<|image_pad|>",
219
+ "<|video_pad|>"
220
+ ],
221
+ "auto_map": {
222
+ "AutoProcessor": "DAMO-NLP-SG/VideoLLaMA3-7B--processing_videollama3.Videollama3Qwen2Processor"
223
+ },
224
+ "bos_token": null,
225
+ "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}\n {% if 'time' in content %}\n {{- 'Time ' + content['time'] | round(1) | string + 's: ' -}}\n {% endif %}\n\n {{- '<image>\n' -}}\n\n {% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n\n {{- '<image>,' -}}\n\n {% else %}\n\n {{- '<image>\n' -}}\n\n {% endif %}\n {% endfor %}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% endif %}\n {% endfor %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
226
+ "clean_up_tokenization_spaces": false,
227
+ "eos_token": "<|im_end|>",
228
+ "errors": "replace",
229
+ "model_max_length": 16384,
230
+ "pad_token": "<|endoftext|>",
231
+ "padding_side": "right",
232
+ "processor_class": "Videollama3Qwen2Processor",
233
+ "split_special_tokens": false,
234
+ "tokenizer_class": "Qwen2Tokenizer",
235
+ "unk_token": null
236
+ }
trainer_state.json ADDED
@@ -0,0 +1,740 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9911678115799804,
5
+ "eval_steps": 500,
6
+ "global_step": 101,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009813542688910697,
13
+ "grad_norm": 2.8672487474187687,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 2.1544,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019627085377821395,
20
+ "grad_norm": 2.754588790109863,
21
+ "learning_rate": 5e-06,
22
+ "loss": 2.142,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.029440628066732092,
27
+ "grad_norm": 2.590669275853557,
28
+ "learning_rate": 7.500000000000001e-06,
29
+ "loss": 1.9074,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03925417075564279,
34
+ "grad_norm": 1.912791537410904,
35
+ "learning_rate": 1e-05,
36
+ "loss": 1.733,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04906771344455348,
41
+ "grad_norm": 1.2960446152840717,
42
+ "learning_rate": 9.997377845227577e-06,
43
+ "loss": 1.4053,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.058881256133464184,
48
+ "grad_norm": 1.5094470155263513,
49
+ "learning_rate": 9.98951413118856e-06,
50
+ "loss": 1.24,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06869479882237488,
55
+ "grad_norm": 1.4729523990902567,
56
+ "learning_rate": 9.97641710583307e-06,
57
+ "loss": 1.1846,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.07850834151128558,
62
+ "grad_norm": 0.6192450033938127,
63
+ "learning_rate": 9.958100506132127e-06,
64
+ "loss": 1.2066,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08832188420019627,
69
+ "grad_norm": 0.5248188615161075,
70
+ "learning_rate": 9.934583543669454e-06,
71
+ "loss": 0.9077,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09813542688910697,
76
+ "grad_norm": 0.4652794249979759,
77
+ "learning_rate": 9.905890884491196e-06,
78
+ "loss": 0.8559,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10794896957801767,
83
+ "grad_norm": 0.524548716007966,
84
+ "learning_rate": 9.872052623234632e-06,
85
+ "loss": 0.9704,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.11776251226692837,
90
+ "grad_norm": 0.5314194335904315,
91
+ "learning_rate": 9.833104251563058e-06,
92
+ "loss": 0.9223,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.12757605495583907,
97
+ "grad_norm": 0.3047635309199024,
98
+ "learning_rate": 9.789086620939936e-06,
99
+ "loss": 0.9302,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.13738959764474976,
104
+ "grad_norm": 0.3819529820066455,
105
+ "learning_rate": 9.740045899781353e-06,
106
+ "loss": 0.8211,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.14720314033366044,
111
+ "grad_norm": 0.39909585000271475,
112
+ "learning_rate": 9.68603352503172e-06,
113
+ "loss": 0.8913,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.15701668302257116,
118
+ "grad_norm": 0.3479302056108582,
119
+ "learning_rate": 9.627106148213521e-06,
120
+ "loss": 0.9723,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.16683022571148184,
125
+ "grad_norm": 0.3766959942077643,
126
+ "learning_rate": 9.563325576007702e-06,
127
+ "loss": 0.8522,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.17664376840039253,
132
+ "grad_norm": 0.2857198795401394,
133
+ "learning_rate": 9.494758705426978e-06,
134
+ "loss": 0.9633,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.18645731108930325,
139
+ "grad_norm": 0.2993174163090425,
140
+ "learning_rate": 9.421477453650118e-06,
141
+ "loss": 0.8605,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.19627085377821393,
146
+ "grad_norm": 0.3107401663608036,
147
+ "learning_rate": 9.343558682590757e-06,
148
+ "loss": 0.8296,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.20608439646712462,
153
+ "grad_norm": 0.3270368688125023,
154
+ "learning_rate": 9.261084118279846e-06,
155
+ "loss": 0.8632,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.21589793915603533,
160
+ "grad_norm": 0.32890526306764684,
161
+ "learning_rate": 9.174140265146356e-06,
162
+ "loss": 0.954,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.22571148184494602,
167
+ "grad_norm": 0.2208062222434778,
168
+ "learning_rate": 9.082818315286054e-06,
169
+ "loss": 0.7973,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.23552502453385674,
174
+ "grad_norm": 0.23994712657664863,
175
+ "learning_rate": 8.987214052813605e-06,
176
+ "loss": 0.8003,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.24533856722276742,
181
+ "grad_norm": 0.3579410121713744,
182
+ "learning_rate": 8.887427753398249e-06,
183
+ "loss": 0.9163,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.25515210991167814,
188
+ "grad_norm": 0.25858791865785286,
189
+ "learning_rate": 8.783564079088478e-06,
190
+ "loss": 0.9203,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.2649656526005888,
195
+ "grad_norm": 0.2221965052804783,
196
+ "learning_rate": 8.675731968536004e-06,
197
+ "loss": 0.7986,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.2747791952894995,
202
+ "grad_norm": 0.25869875995203495,
203
+ "learning_rate": 8.564044522734147e-06,
204
+ "loss": 0.8584,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.2845927379784102,
209
+ "grad_norm": 0.25639549077125273,
210
+ "learning_rate": 8.448618886390523e-06,
211
+ "loss": 0.9153,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2944062806673209,
216
+ "grad_norm": 0.28969420637722326,
217
+ "learning_rate": 8.329576125058406e-06,
218
+ "loss": 1.0017,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.3042198233562316,
223
+ "grad_norm": 0.27142079291709187,
224
+ "learning_rate": 8.207041098155701e-06,
225
+ "loss": 0.8834,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.3140333660451423,
230
+ "grad_norm": 0.24855994809239515,
231
+ "learning_rate": 8.081142328004638e-06,
232
+ "loss": 0.8804,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.323846908734053,
237
+ "grad_norm": 0.2932484533076321,
238
+ "learning_rate": 7.952011865029614e-06,
239
+ "loss": 0.8055,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.3336604514229637,
244
+ "grad_norm": 0.2899949936434053,
245
+ "learning_rate": 7.819785149254534e-06,
246
+ "loss": 0.7479,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3434739941118744,
251
+ "grad_norm": 0.23167648356664933,
252
+ "learning_rate": 7.68460086824492e-06,
253
+ "loss": 0.8886,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.35328753680078506,
258
+ "grad_norm": 0.2640358818005348,
259
+ "learning_rate": 7.546600811643816e-06,
260
+ "loss": 0.9551,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3631010794896958,
265
+ "grad_norm": 0.2595883854771292,
266
+ "learning_rate": 7.405929722454026e-06,
267
+ "loss": 0.9107,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3729146221786065,
272
+ "grad_norm": 0.2471525297780812,
273
+ "learning_rate": 7.262735145222696e-06,
274
+ "loss": 0.8207,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.38272816486751715,
279
+ "grad_norm": 0.2476329062250312,
280
+ "learning_rate": 7.117167271287453e-06,
281
+ "loss": 0.854,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.39254170755642787,
286
+ "grad_norm": 0.26094540269164535,
287
+ "learning_rate": 6.969378781246436e-06,
288
+ "loss": 0.876,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.4023552502453386,
293
+ "grad_norm": 0.26106316938836766,
294
+ "learning_rate": 6.819524684817439e-06,
295
+ "loss": 0.8629,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.41216879293424924,
300
+ "grad_norm": 0.23060264618437654,
301
+ "learning_rate": 6.667762158254104e-06,
302
+ "loss": 0.8538,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.42198233562315995,
307
+ "grad_norm": 0.24185186221890845,
308
+ "learning_rate": 6.514250379489754e-06,
309
+ "loss": 0.9191,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.43179587831207067,
314
+ "grad_norm": 0.2393529024626251,
315
+ "learning_rate": 6.3591503611817155e-06,
316
+ "loss": 0.8808,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.44160942100098133,
321
+ "grad_norm": 0.2605127572935315,
322
+ "learning_rate": 6.202624781831269e-06,
323
+ "loss": 0.8904,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.45142296368989204,
328
+ "grad_norm": 0.2480445894592462,
329
+ "learning_rate": 6.044837815156377e-06,
330
+ "loss": 0.8717,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.46123650637880276,
335
+ "grad_norm": 0.2598210274633706,
336
+ "learning_rate": 5.885954957896115e-06,
337
+ "loss": 0.8659,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.47105004906771347,
342
+ "grad_norm": 0.25886899490619003,
343
+ "learning_rate": 5.726142856227453e-06,
344
+ "loss": 0.9661,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.48086359175662413,
349
+ "grad_norm": 0.27445286917757566,
350
+ "learning_rate": 5.5655691309764225e-06,
351
+ "loss": 0.7741,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.49067713444553485,
356
+ "grad_norm": 0.2998354383728768,
357
+ "learning_rate": 5.404402201807022e-06,
358
+ "loss": 0.7016,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.5004906771344455,
363
+ "grad_norm": 0.30281526320811003,
364
+ "learning_rate": 5.242811110572243e-06,
365
+ "loss": 0.8998,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.5103042198233563,
370
+ "grad_norm": 0.23291295344605198,
371
+ "learning_rate": 5.080965344012509e-06,
372
+ "loss": 0.8599,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.5201177625122669,
377
+ "grad_norm": 0.2564082609308688,
378
+ "learning_rate": 4.919034655987493e-06,
379
+ "loss": 0.8412,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.5299313052011776,
384
+ "grad_norm": 0.27404998782840256,
385
+ "learning_rate": 4.757188889427761e-06,
386
+ "loss": 0.8401,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5397448478900884,
391
+ "grad_norm": 0.25818007029770623,
392
+ "learning_rate": 4.59559779819298e-06,
393
+ "loss": 0.9063,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.549558390578999,
398
+ "grad_norm": 0.26623848076266293,
399
+ "learning_rate": 4.434430869023579e-06,
400
+ "loss": 0.7651,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5593719332679097,
405
+ "grad_norm": 0.2658949551049741,
406
+ "learning_rate": 4.27385714377255e-06,
407
+ "loss": 0.9671,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5691854759568205,
412
+ "grad_norm": 0.2954557630383791,
413
+ "learning_rate": 4.1140450421038865e-06,
414
+ "loss": 0.8364,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5789990186457311,
419
+ "grad_norm": 0.24989225651779404,
420
+ "learning_rate": 3.955162184843625e-06,
421
+ "loss": 0.8642,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5888125613346418,
426
+ "grad_norm": 0.2540070747708594,
427
+ "learning_rate": 3.7973752181687336e-06,
428
+ "loss": 0.9487,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5986261040235525,
433
+ "grad_norm": 0.2875487613543649,
434
+ "learning_rate": 3.6408496388182857e-06,
435
+ "loss": 0.8931,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.6084396467124632,
440
+ "grad_norm": 0.25257746440863926,
441
+ "learning_rate": 3.4857496205102475e-06,
442
+ "loss": 0.7283,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.6182531894013739,
447
+ "grad_norm": 0.2612423385739647,
448
+ "learning_rate": 3.3322378417458985e-06,
449
+ "loss": 0.8973,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.6280667320902846,
454
+ "grad_norm": 0.2863739428894319,
455
+ "learning_rate": 3.180475315182563e-06,
456
+ "loss": 0.8244,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.6378802747791953,
461
+ "grad_norm": 0.25895617346448274,
462
+ "learning_rate": 3.0306212187535653e-06,
463
+ "loss": 0.8444,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.647693817468106,
468
+ "grad_norm": 0.25861219708555827,
469
+ "learning_rate": 2.882832728712551e-06,
470
+ "loss": 0.9331,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6575073601570167,
475
+ "grad_norm": 0.259266449527201,
476
+ "learning_rate": 2.7372648547773063e-06,
477
+ "loss": 0.9111,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6673209028459274,
482
+ "grad_norm": 0.2536619784605648,
483
+ "learning_rate": 2.594070277545975e-06,
484
+ "loss": 0.8717,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.677134445534838,
489
+ "grad_norm": 0.26066935129753177,
490
+ "learning_rate": 2.4533991883561868e-06,
491
+ "loss": 0.7797,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6869479882237488,
496
+ "grad_norm": 0.2517815528639677,
497
+ "learning_rate": 2.315399131755081e-06,
498
+ "loss": 0.8631,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6967615309126595,
503
+ "grad_norm": 0.25996941562937426,
504
+ "learning_rate": 2.1802148507454675e-06,
505
+ "loss": 0.8719,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.7065750736015701,
510
+ "grad_norm": 0.24588266413337945,
511
+ "learning_rate": 2.0479881349703885e-06,
512
+ "loss": 0.9193,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.7163886162904809,
517
+ "grad_norm": 0.2745377438843979,
518
+ "learning_rate": 1.9188576719953635e-06,
519
+ "loss": 0.861,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.7262021589793916,
524
+ "grad_norm": 0.22640992501852827,
525
+ "learning_rate": 1.7929589018443016e-06,
526
+ "loss": 0.7663,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.7360157016683022,
531
+ "grad_norm": 0.24363259853967661,
532
+ "learning_rate": 1.6704238749415958e-06,
533
+ "loss": 0.7472,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.745829244357213,
538
+ "grad_norm": 0.2777670891337088,
539
+ "learning_rate": 1.5513811136094786e-06,
540
+ "loss": 0.9389,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7556427870461236,
545
+ "grad_norm": 0.26198217510926863,
546
+ "learning_rate": 1.4359554772658551e-06,
547
+ "loss": 0.8868,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7654563297350343,
552
+ "grad_norm": 0.25420697034959644,
553
+ "learning_rate": 1.3242680314639995e-06,
554
+ "loss": 0.7417,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7752698724239451,
559
+ "grad_norm": 0.27383288657704047,
560
+ "learning_rate": 1.2164359209115235e-06,
561
+ "loss": 0.7767,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.7850834151128557,
566
+ "grad_norm": 0.26155693194049967,
567
+ "learning_rate": 1.1125722466017547e-06,
568
+ "loss": 0.8705,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7948969578017664,
573
+ "grad_norm": 0.2892989585599706,
574
+ "learning_rate": 1.012785947186397e-06,
575
+ "loss": 0.8472,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.8047105004906772,
580
+ "grad_norm": 0.257453864175166,
581
+ "learning_rate": 9.171816847139447e-07,
582
+ "loss": 0.9102,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.8145240431795878,
587
+ "grad_norm": 0.25933961134109923,
588
+ "learning_rate": 8.258597348536452e-07,
589
+ "loss": 0.8377,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.8243375858684985,
594
+ "grad_norm": 0.2504962150041825,
595
+ "learning_rate": 7.389158817201541e-07,
596
+ "loss": 0.8331,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.8341511285574092,
601
+ "grad_norm": 0.2420056571684986,
602
+ "learning_rate": 6.564413174092443e-07,
603
+ "loss": 0.8771,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.8439646712463199,
608
+ "grad_norm": 0.23509290212940573,
609
+ "learning_rate": 5.785225463498828e-07,
610
+ "loss": 0.8197,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.8537782139352306,
615
+ "grad_norm": 0.26997192628106204,
616
+ "learning_rate": 5.05241294573024e-07,
617
+ "loss": 0.8369,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8635917566241413,
622
+ "grad_norm": 0.2820942983849838,
623
+ "learning_rate": 4.3667442399229985e-07,
624
+ "loss": 0.7722,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.873405299313052,
629
+ "grad_norm": 0.2516407661322018,
630
+ "learning_rate": 3.728938517864794e-07,
631
+ "loss": 0.8593,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.8832188420019627,
636
+ "grad_norm": 0.26231652652086895,
637
+ "learning_rate": 3.1396647496828245e-07,
638
+ "loss": 0.8056,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8930323846908734,
643
+ "grad_norm": 0.27028297041866356,
644
+ "learning_rate": 2.599541002186479e-07,
645
+ "loss": 0.7567,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.9028459273797841,
650
+ "grad_norm": 0.23972498640175965,
651
+ "learning_rate": 2.109133790600648e-07,
652
+ "loss": 0.8646,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.9126594700686947,
657
+ "grad_norm": 0.25770792802506376,
658
+ "learning_rate": 1.6689574843694433e-07,
659
+ "loss": 0.8596,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.9224730127576055,
664
+ "grad_norm": 0.25190515551071735,
665
+ "learning_rate": 1.2794737676536993e-07,
666
+ "loss": 0.711,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.9322865554465162,
671
+ "grad_norm": 0.24771560518251803,
672
+ "learning_rate": 9.410911550880474e-08,
673
+ "loss": 0.8539,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.9421000981354269,
678
+ "grad_norm": 0.2534003058388717,
679
+ "learning_rate": 6.54164563305465e-08,
680
+ "loss": 0.8507,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.9519136408243376,
685
+ "grad_norm": 0.27958663472352846,
686
+ "learning_rate": 4.189949386787462e-08,
687
+ "loss": 0.7761,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.9617271835132483,
692
+ "grad_norm": 0.28280544357692566,
693
+ "learning_rate": 2.358289416693027e-08,
694
+ "loss": 0.8915,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.971540726202159,
699
+ "grad_norm": 0.251854611552598,
700
+ "learning_rate": 1.0485868811441757e-08,
701
+ "loss": 0.9458,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9813542688910697,
706
+ "grad_norm": 0.2651175828136124,
707
+ "learning_rate": 2.6221547724253337e-09,
708
+ "loss": 0.7782,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9911678115799804,
713
+ "grad_norm": 0.262045684118293,
714
+ "learning_rate": 0.0,
715
+ "loss": 0.7791,
716
+ "step": 101
717
+ }
718
+ ],
719
+ "logging_steps": 1.0,
720
+ "max_steps": 101,
721
+ "num_input_tokens_seen": 0,
722
+ "num_train_epochs": 1,
723
+ "save_steps": 500,
724
+ "stateful_callbacks": {
725
+ "TrainerControl": {
726
+ "args": {
727
+ "should_epoch_stop": false,
728
+ "should_evaluate": false,
729
+ "should_log": false,
730
+ "should_save": true,
731
+ "should_training_stop": true
732
+ },
733
+ "attributes": {}
734
+ }
735
+ },
736
+ "total_flos": 412567592239104.0,
737
+ "train_batch_size": 2,
738
+ "trial_name": null,
739
+ "trial_params": null
740
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad6f625727d6eab01a3ba878dc8ddbb2e6ce03da356743ee2375ecb93cf1d3cd
3
+ size 7608
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
zero_to_fp32.py ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import json
25
+ from tqdm import tqdm
26
+ from collections import OrderedDict
27
+ from dataclasses import dataclass
28
+
29
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
30
+ # DeepSpeed data structures it has to be available in the current python environment.
31
+ from deepspeed.utils import logger
32
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
33
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
34
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
35
+
36
+
37
+ @dataclass
38
+ class zero_model_state:
39
+ buffers: dict()
40
+ param_shapes: dict()
41
+ shared_params: list
42
+ ds_version: int
43
+ frozen_param_shapes: dict()
44
+ frozen_param_fragments: dict()
45
+
46
+
47
+ debug = 0
48
+
49
+ # load to cpu
50
+ device = torch.device('cpu')
51
+
52
+
53
+ def atoi(text):
54
+ return int(text) if text.isdigit() else text
55
+
56
+
57
+ def natural_keys(text):
58
+ '''
59
+ alist.sort(key=natural_keys) sorts in human order
60
+ http://nedbatchelder.com/blog/200712/human_sorting.html
61
+ (See Toothy's implementation in the comments)
62
+ '''
63
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
64
+
65
+
66
+ def get_model_state_file(checkpoint_dir, zero_stage):
67
+ if not os.path.isdir(checkpoint_dir):
68
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
69
+
70
+ # there should be only one file
71
+ if zero_stage <= 2:
72
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
73
+ elif zero_stage == 3:
74
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
75
+
76
+ if not os.path.exists(file):
77
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
78
+
79
+ return file
80
+
81
+
82
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
83
+ # XXX: need to test that this simple glob rule works for multi-node setup too
84
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
85
+
86
+ if len(ckpt_files) == 0:
87
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
88
+
89
+ return ckpt_files
90
+
91
+
92
+ def get_optim_files(checkpoint_dir):
93
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
94
+
95
+
96
+ def get_model_state_files(checkpoint_dir):
97
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
98
+
99
+
100
+ def parse_model_states(files):
101
+ zero_model_states = []
102
+ for file in files:
103
+ state_dict = torch.load(file, map_location=device)
104
+
105
+ if BUFFER_NAMES not in state_dict:
106
+ raise ValueError(f"{file} is not a model state checkpoint")
107
+ buffer_names = state_dict[BUFFER_NAMES]
108
+ if debug:
109
+ print("Found buffers:", buffer_names)
110
+
111
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
112
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
113
+ param_shapes = state_dict[PARAM_SHAPES]
114
+
115
+ # collect parameters that are included in param_shapes
116
+ param_names = []
117
+ for s in param_shapes:
118
+ for name in s.keys():
119
+ param_names.append(name)
120
+
121
+ # update with frozen parameters
122
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
123
+ if frozen_param_shapes is not None:
124
+ if debug:
125
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
126
+ param_names += list(frozen_param_shapes.keys())
127
+
128
+ # handle shared params
129
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
130
+
131
+ ds_version = state_dict.get(DS_VERSION, None)
132
+
133
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
134
+
135
+ z_model_state = zero_model_state(buffers=buffers,
136
+ param_shapes=param_shapes,
137
+ shared_params=shared_params,
138
+ ds_version=ds_version,
139
+ frozen_param_shapes=frozen_param_shapes,
140
+ frozen_param_fragments=frozen_param_fragments)
141
+ zero_model_states.append(z_model_state)
142
+
143
+ return zero_model_states
144
+
145
+
146
+ def parse_optim_states(files, ds_checkpoint_dir):
147
+ total_files = len(files)
148
+ state_dicts = []
149
+ for f in files:
150
+ state_dict = torch.load(f, map_location=device)
151
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
152
+ # and also handle the case where it was already removed by another helper script
153
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
154
+ state_dicts.append(state_dict)
155
+
156
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
157
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
158
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
159
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
160
+
161
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
162
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
163
+ # use the max of the partition_count to get the dp world_size.
164
+
165
+ if type(world_size) is list:
166
+ world_size = max(world_size)
167
+
168
+ if world_size != total_files:
169
+ raise ValueError(
170
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
171
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
172
+ )
173
+
174
+ # the groups are named differently in each stage
175
+ if zero_stage <= 2:
176
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
177
+ elif zero_stage == 3:
178
+ fp32_groups_key = FP32_FLAT_GROUPS
179
+ else:
180
+ raise ValueError(f"unknown zero stage {zero_stage}")
181
+
182
+ if zero_stage <= 2:
183
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
184
+ elif zero_stage == 3:
185
+ # if there is more than one param group, there will be multiple flattened tensors - one
186
+ # flattened tensor per group - for simplicity merge them into a single tensor
187
+ #
188
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
189
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
190
+
191
+ fp32_flat_groups = [
192
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
193
+ ]
194
+
195
+ return zero_stage, world_size, fp32_flat_groups
196
+
197
+
198
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
199
+ """
200
+ Returns fp32 state_dict reconstructed from ds checkpoint
201
+
202
+ Args:
203
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
204
+
205
+ """
206
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
207
+
208
+ optim_files = get_optim_files(ds_checkpoint_dir)
209
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
210
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
211
+
212
+ model_files = get_model_state_files(ds_checkpoint_dir)
213
+
214
+ zero_model_states = parse_model_states(model_files)
215
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
216
+
217
+ if zero_stage <= 2:
218
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
219
+ exclude_frozen_parameters)
220
+ elif zero_stage == 3:
221
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
222
+ exclude_frozen_parameters)
223
+
224
+
225
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
226
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
227
+ return
228
+
229
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
230
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
231
+
232
+ if debug:
233
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
234
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
235
+
236
+ wanted_params = len(frozen_param_shapes)
237
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
238
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
239
+ print(f'Frozen params: Have {avail_numel} numels to process.')
240
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
241
+
242
+ total_params = 0
243
+ total_numel = 0
244
+ for name, shape in frozen_param_shapes.items():
245
+ total_params += 1
246
+ unpartitioned_numel = shape.numel()
247
+ total_numel += unpartitioned_numel
248
+
249
+ state_dict[name] = frozen_param_fragments[name]
250
+
251
+ if debug:
252
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
253
+
254
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
255
+
256
+
257
+ def _has_callable(obj, fn):
258
+ attr = getattr(obj, fn, None)
259
+ return callable(attr)
260
+
261
+
262
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
263
+ param_shapes = zero_model_states[0].param_shapes
264
+
265
+ # Reconstruction protocol:
266
+ #
267
+ # XXX: document this
268
+
269
+ if debug:
270
+ for i in range(world_size):
271
+ for j in range(len(fp32_flat_groups[0])):
272
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
273
+
274
+ # XXX: memory usage doubles here (zero2)
275
+ num_param_groups = len(fp32_flat_groups[0])
276
+ merged_single_partition_of_fp32_groups = []
277
+ for i in range(num_param_groups):
278
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
279
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
280
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
281
+ avail_numel = sum(
282
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
283
+
284
+ if debug:
285
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
286
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
287
+ # not asserting if there is a mismatch due to possible padding
288
+ print(f"Have {avail_numel} numels to process.")
289
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
290
+
291
+ # params
292
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
293
+ # out-of-core computing solution
294
+ total_numel = 0
295
+ total_params = 0
296
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
297
+ offset = 0
298
+ avail_numel = full_single_fp32_vector.numel()
299
+ for name, shape in shapes.items():
300
+
301
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
302
+ total_numel += unpartitioned_numel
303
+ total_params += 1
304
+
305
+ if debug:
306
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
307
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
308
+ offset += unpartitioned_numel
309
+
310
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
311
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
312
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
313
+ # live optimizer object, so we are checking that the numbers are within the right range
314
+ align_to = 2 * world_size
315
+
316
+ def zero2_align(x):
317
+ return align_to * math.ceil(x / align_to)
318
+
319
+ if debug:
320
+ print(f"original offset={offset}, avail_numel={avail_numel}")
321
+
322
+ offset = zero2_align(offset)
323
+ avail_numel = zero2_align(avail_numel)
324
+
325
+ if debug:
326
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
327
+
328
+ # Sanity check
329
+ if offset != avail_numel:
330
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
331
+
332
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
333
+
334
+
335
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
336
+ exclude_frozen_parameters):
337
+ state_dict = OrderedDict()
338
+
339
+ # buffers
340
+ buffers = zero_model_states[0].buffers
341
+ state_dict.update(buffers)
342
+ if debug:
343
+ print(f"added {len(buffers)} buffers")
344
+
345
+ if not exclude_frozen_parameters:
346
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
347
+
348
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
349
+
350
+ # recover shared parameters
351
+ for pair in zero_model_states[0].shared_params:
352
+ if pair[1] in state_dict:
353
+ state_dict[pair[0]] = state_dict[pair[1]]
354
+
355
+ return state_dict
356
+
357
+
358
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
359
+ remainder = unpartitioned_numel % world_size
360
+ padding_numel = (world_size - remainder) if remainder else 0
361
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
362
+ return partitioned_numel, padding_numel
363
+
364
+
365
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
366
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
367
+ return
368
+
369
+ if debug:
370
+ for i in range(world_size):
371
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
372
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
373
+
374
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
375
+ wanted_params = len(frozen_param_shapes)
376
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
377
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
378
+ print(f'Frozen params: Have {avail_numel} numels to process.')
379
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
380
+
381
+ total_params = 0
382
+ total_numel = 0
383
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
384
+ total_params += 1
385
+ unpartitioned_numel = shape.numel()
386
+ total_numel += unpartitioned_numel
387
+
388
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
389
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
390
+
391
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
392
+
393
+ if debug:
394
+ print(
395
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
396
+ )
397
+
398
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
399
+
400
+
401
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
402
+ param_shapes = zero_model_states[0].param_shapes
403
+ avail_numel = fp32_flat_groups[0].numel() * world_size
404
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
405
+ # param, re-consolidating each param, while dealing with padding if any
406
+
407
+ # merge list of dicts, preserving order
408
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
409
+
410
+ if debug:
411
+ for i in range(world_size):
412
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
413
+
414
+ wanted_params = len(param_shapes)
415
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
416
+ # not asserting if there is a mismatch due to possible padding
417
+ avail_numel = fp32_flat_groups[0].numel() * world_size
418
+ print(f"Trainable params: Have {avail_numel} numels to process.")
419
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
420
+
421
+ # params
422
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
423
+ # out-of-core computing solution
424
+ offset = 0
425
+ total_numel = 0
426
+ total_params = 0
427
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
428
+ unpartitioned_numel = shape.numel()
429
+ total_numel += unpartitioned_numel
430
+ total_params += 1
431
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
432
+
433
+ if debug:
434
+ print(
435
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
436
+ )
437
+
438
+ # XXX: memory usage doubles here
439
+ state_dict[name] = torch.cat(
440
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
441
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
442
+ offset += partitioned_numel
443
+
444
+ offset *= world_size
445
+
446
+ # Sanity check
447
+ if offset != avail_numel:
448
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
449
+
450
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
451
+
452
+
453
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
454
+ exclude_frozen_parameters):
455
+ state_dict = OrderedDict()
456
+
457
+ # buffers
458
+ buffers = zero_model_states[0].buffers
459
+ state_dict.update(buffers)
460
+ if debug:
461
+ print(f"added {len(buffers)} buffers")
462
+
463
+ if not exclude_frozen_parameters:
464
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
465
+
466
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
467
+
468
+ # recover shared parameters
469
+ for pair in zero_model_states[0].shared_params:
470
+ if pair[1] in state_dict:
471
+ state_dict[pair[0]] = state_dict[pair[1]]
472
+
473
+ return state_dict
474
+
475
+
476
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
477
+ """
478
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
479
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
480
+ via a model hub.
481
+
482
+ Args:
483
+ - ``checkpoint_dir``: path to the desired checkpoint folder
484
+ - ``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``
485
+ - ``exclude_frozen_parameters``: exclude frozen parameters
486
+
487
+ Returns:
488
+ - pytorch ``state_dict``
489
+
490
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
491
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
492
+ the checkpoint.
493
+
494
+ A typical usage might be ::
495
+
496
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
497
+ # do the training and checkpoint saving
498
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
499
+ model = model.cpu() # move to cpu
500
+ model.load_state_dict(state_dict)
501
+ # submit to model hub or save the model to share with others
502
+
503
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
504
+ application. i.e. you will need to re-initialize the deepspeed engine, since
505
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
506
+
507
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
508
+
509
+ """
510
+ if tag is None:
511
+ latest_path = os.path.join(checkpoint_dir, 'latest')
512
+ if os.path.isfile(latest_path):
513
+ with open(latest_path, 'r') as fd:
514
+ tag = fd.read().strip()
515
+ else:
516
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
517
+
518
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
519
+
520
+ if not os.path.isdir(ds_checkpoint_dir):
521
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
522
+
523
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
524
+
525
+
526
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
527
+ output_dir,
528
+ max_shard_size="5GB",
529
+ safe_serialization=False,
530
+ tag=None,
531
+ exclude_frozen_parameters=False):
532
+ """
533
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
534
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
535
+
536
+ Args:
537
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
538
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
539
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
540
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
541
+ - ``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``
542
+ - ``exclude_frozen_parameters``: exclude frozen parameters
543
+ """
544
+ # Dependency pre-check
545
+ if safe_serialization:
546
+ try:
547
+ from safetensors.torch import save_file
548
+ except ImportError:
549
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
550
+ raise
551
+ if max_shard_size is not None:
552
+ try:
553
+ from huggingface_hub import split_torch_state_dict_into_shards
554
+ except ImportError:
555
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
556
+ raise
557
+
558
+ # Convert zero checkpoint to state_dict
559
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
560
+
561
+ # Shard the model if it is too big.
562
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
563
+ if max_shard_size is not None:
564
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
565
+ state_dict_split = split_torch_state_dict_into_shards(state_dict,
566
+ filename_pattern=filename_pattern,
567
+ max_shard_size=max_shard_size)
568
+ else:
569
+ from collections import namedtuple
570
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
571
+ state_dict_split = StateDictSplit(is_sharded=False,
572
+ filename_to_tensors={weights_name: list(state_dict.keys())})
573
+
574
+ # Save the model
575
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
576
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
577
+ shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
578
+ output_path = os.path.join(output_dir, shard_file)
579
+ if safe_serialization:
580
+ save_file(shard, output_path, metadata={"format": "pt"})
581
+ else:
582
+ torch.save(shard, output_path)
583
+
584
+ # Save index if sharded
585
+ if state_dict_split.is_sharded:
586
+ index = {
587
+ "metadata": state_dict_split.metadata,
588
+ "weight_map": state_dict_split.tensor_to_filename,
589
+ }
590
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
591
+ save_index_file = os.path.join(output_dir, save_index_file)
592
+ with open(save_index_file, "w", encoding="utf-8") as f:
593
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
594
+ f.write(content)
595
+
596
+
597
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
598
+ """
599
+ 1. Put the provided model to cpu
600
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
601
+ 3. Load it into the provided model
602
+
603
+ Args:
604
+ - ``model``: the model object to update
605
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
606
+ - ``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``
607
+
608
+ Returns:
609
+ - ``model`: modified model
610
+
611
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
612
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
613
+ conveniently placed for you in the checkpoint folder.
614
+
615
+ A typical usage might be ::
616
+
617
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
618
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
619
+ # submit to model hub or save the model to share with others
620
+
621
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
622
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
623
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
624
+
625
+ """
626
+ logger.info(f"Extracting fp32 weights")
627
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
628
+
629
+ logger.info(f"Overwriting model with fp32 weights")
630
+ model = model.cpu()
631
+ model.load_state_dict(state_dict, strict=False)
632
+
633
+ return model
634
+
635
+
636
+ if __name__ == "__main__":
637
+ parser = argparse.ArgumentParser()
638
+ parser.add_argument("checkpoint_dir",
639
+ type=str,
640
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
641
+ parser.add_argument("output_dir",
642
+ type=str,
643
+ help="directory to the pytorch fp32 state_dict output files"
644
+ "(e.g. path/checkpoint-12-output/)")
645
+ parser.add_argument(
646
+ "--max_shard_size",
647
+ type=str,
648
+ default="5GB",
649
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
650
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
651
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
652
+ "without CPU OOM issues.")
653
+ parser.add_argument(
654
+ "--safe_serialization",
655
+ default=False,
656
+ action='store_true',
657
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
658
+ parser.add_argument("-t",
659
+ "--tag",
660
+ type=str,
661
+ default=None,
662
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
663
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
664
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
665
+ args = parser.parse_args()
666
+
667
+ debug = args.debug
668
+
669
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
670
+ args.output_dir,
671
+ max_shard_size=args.max_shard_size,
672
+ safe_serialization=args.safe_serialization,
673
+ tag=args.tag,
674
+ exclude_frozen_parameters=args.exclude_frozen_parameters)