Hugging Face's logo

Ilus-AI
/
Qwen-Image-2512-FP8

Text-to-Image
Diffusers
QwenImagePipeline
quantization
torchao
fp8
Model card Files
xet
 Community
1
Ilus-AI commited on
Commit
352c5dc
·
verified ·
1 Parent(s): d03ce2e

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. README.md +69 -0
  3. model_index.json +25 -0
  4. scheduler/scheduler_config.json +18 -0
  5. test_output.png +3 -0
  6. text_encoder/config.json +152 -0
  7. text_encoder/generation_config.json +6 -0
  8. text_encoder/pytorch_model-00001-of-00002.bin +3 -0
  9. text_encoder/pytorch_model-00002-of-00002.bin +3 -0
  10. text_encoder/pytorch_model.bin.index.json +737 -0
  11. tokenizer/added_tokens.json +24 -0
  12. tokenizer/chat_template.jinja +54 -0
  13. tokenizer/merges.txt +0 -0
  14. tokenizer/special_tokens_map.json +31 -0
  15. tokenizer/tokenizer_config.json +207 -0
  16. tokenizer/vocab.json +0 -0
  17. transformer/config.json +39 -0
  18. transformer/diffusion_pytorch_model-00001-of-00003.bin +3 -0
  19. transformer/diffusion_pytorch_model-00002-of-00003.bin +3 -0
  20. transformer/diffusion_pytorch_model-00003-of-00003.bin +3 -0
  21. transformer/diffusion_pytorch_model.bin.index.json +0 -0
  22. vae/config.json +58 -0
  23. vae/diffusion_pytorch_model.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ test_output.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen-Image-2512
4
+ tags:
5
+ - diffusers
6
+ - text-to-image
7
+ - quantization
8
+ - torchao
9
+ - fp8
10
+ library_name: diffusers
11
+ pipeline_tag: text-to-image
12
+ ---
13
+
14
+ # Qwen-Image-2512-FP8
15
+
16
+ FP8 quantized version of [Qwen/Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) using torchao.
17
+
18
+ ## Quantized Components
19
+ - ✅ Transformer: FP8 weight-only
20
+ - ✅ Text Encoder: FP8 weight-only
21
+
22
+ ## Requirements
23
+
24
+ ```bash
25
+ pip install torch diffusers transformers torchao accelerate
26
+ ```
27
+
28
+ ## Usage
29
+
30
+ ```python
31
+ import torch
32
+ from diffusers import DiffusionPipeline
33
+
34
+ pipe = DiffusionPipeline.from_pretrained(
35
+ "Ilus-AI/Qwen-Image-2512-FP8",
36
+ torch_dtype=torch.bfloat16,
37
+ use_safetensors=False,
38
+ device_map="balanced"
39
+ )
40
+
41
+ prompt = "A 20-year-old East Asian girl with delicate features and bright brown eyes, naturally wavy long hair, wearing a modern cute dress in soft colors, vivid youthful charm"
42
+ negative_prompt = "low resolution, low quality, distorted, blurry"
43
+
44
+ image = pipe(
45
+ prompt=prompt,
46
+ negative_prompt=negative_prompt,
47
+ width=1664,
48
+ height=928,
49
+ num_inference_steps=50,
50
+ true_cfg_scale=4.0,
51
+ generator=torch.Generator(device="cuda").manual_seed(42)
52
+ ).images[0]
53
+
54
+ image.save("output.png")
55
+ ```
56
+
57
+ ## Supported Resolutions
58
+
59
+ | Ratio | Size |
60
+ |-------|------|
61
+ | 1:1 | 1328x1328 |
62
+ | 16:9 | 1664x928 |
63
+ | 9:16 | 928x1664 |
64
+ | 4:3 | 1472x1104 |
65
+ | 3:4 | 1104x1472 |
66
+
67
+ ## Notes
68
+ - Requires `use_safetensors=False` when loading
69
+ - Best performance on GPUs with compute capability >= 8.9 (RTX 4090, H100, L4)
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImagePipeline",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "Qwen/Qwen-Image-2512",
5
+ "scheduler": [
6
+ "diffusers",
7
+ "FlowMatchEulerDiscreteScheduler"
8
+ ],
9
+ "text_encoder": [
10
+ "transformers",
11
+ "Qwen2_5_VLForConditionalGeneration"
12
+ ],
13
+ "tokenizer": [
14
+ "transformers",
15
+ "Qwen2Tokenizer"
16
+ ],
17
+ "transformer": [
18
+ "diffusers",
19
+ "QwenImageTransformer2DModel"
20
+ ],
21
+ "vae": [
22
+ "diffusers",
23
+ "AutoencoderKLQwenImage"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 8192,
8
+ "max_shift": 0.9,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.02,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
test_output.png ADDED

Git LFS Details

  • SHA256: ee977ed5bf914d6761a4cb686a2b58c0a1c8b3c70aeb24455d6c8890c6e682a0
  • Pointer size: 132 Bytes
  • Size of remote file: 1.49 MB
text_encoder/config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "quantization_config": {
21
+ "include_input_output_embeddings": false,
22
+ "modules_to_not_convert": null,
23
+ "quant_method": "torchao",
24
+ "quant_type": {
25
+ "default": {
26
+ "_data": {
27
+ "set_inductor_config": true,
28
+ "weight_dtype": {
29
+ "_data": "float8_e4m3fn",
30
+ "_type": "torch.dtype"
31
+ }
32
+ },
33
+ "_type": "Float8WeightOnlyConfig",
34
+ "_version": 2
35
+ }
36
+ },
37
+ "quant_type_kwargs": {},
38
+ "untie_embedding_weights": false
39
+ },
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "mrope_section": [
43
+ 16,
44
+ 24,
45
+ 24
46
+ ],
47
+ "rope_type": "default",
48
+ "type": "default"
49
+ },
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": 32768,
52
+ "text_config": {
53
+ "_name_or_path": "/workspace/.cache/huggingface/hub/models--Qwen--Qwen-Image-2512/snapshots/25468b98e3276ca6700de15c6628e51b7de54a26/text_encoder",
54
+ "architectures": [
55
+ "Qwen2_5_VLForConditionalGeneration"
56
+ ],
57
+ "attention_dropout": 0.0,
58
+ "bos_token_id": 151643,
59
+ "dtype": "bfloat16",
60
+ "eos_token_id": 151645,
61
+ "hidden_act": "silu",
62
+ "hidden_size": 3584,
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 18944,
65
+ "layer_types": [
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention"
94
+ ],
95
+ "max_position_embeddings": 128000,
96
+ "max_window_layers": 28,
97
+ "model_type": "qwen2_5_vl_text",
98
+ "num_attention_heads": 28,
99
+ "num_hidden_layers": 28,
100
+ "num_key_value_heads": 4,
101
+ "rms_norm_eps": 1e-06,
102
+ "rope_scaling": {
103
+ "mrope_section": [
104
+ 16,
105
+ 24,
106
+ 24
107
+ ],
108
+ "rope_type": "default",
109
+ "type": "default"
110
+ },
111
+ "rope_theta": 1000000.0,
112
+ "sliding_window": null,
113
+ "use_cache": true,
114
+ "use_sliding_window": false,
115
+ "vision_token_id": 151654,
116
+ "vocab_size": 152064
117
+ },
118
+ "tie_word_embeddings": false,
119
+ "transformers_version": "4.57.3",
120
+ "use_cache": true,
121
+ "use_sliding_window": false,
122
+ "video_token_id": 151656,
123
+ "vision_config": {
124
+ "depth": 32,
125
+ "dtype": "bfloat16",
126
+ "fullatt_block_indexes": [
127
+ 7,
128
+ 15,
129
+ 23,
130
+ 31
131
+ ],
132
+ "hidden_act": "silu",
133
+ "hidden_size": 1280,
134
+ "in_channels": 3,
135
+ "in_chans": 3,
136
+ "initializer_range": 0.02,
137
+ "intermediate_size": 3420,
138
+ "model_type": "qwen2_5_vl",
139
+ "num_heads": 16,
140
+ "out_hidden_size": 3584,
141
+ "patch_size": 14,
142
+ "spatial_merge_size": 2,
143
+ "spatial_patch_size": 14,
144
+ "temporal_patch_size": 2,
145
+ "tokens_per_second": 2,
146
+ "window_size": 112
147
+ },
148
+ "vision_end_token_id": 151653,
149
+ "vision_start_token_id": 151652,
150
+ "vision_token_id": 151654,
151
+ "vocab_size": 152064
152
+ }
text_encoder/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": "4.57.3"
6
+ }
text_encoder/pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72781fc832ff8be80a3b68fbfc5f0fe8a6e9b0e461f88b7d354f1559fc15ed0
3
+ size 4968434042
text_encoder/pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:268b279609b1597ce152e931ae724e380294d7eabdd650e9994b2dfd65310ab2
3
+ size 4423785613
text_encoder/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8292166656,
4
+ "total_size": 9391807488
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
70
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
71
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
74
+ "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
82
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
83
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
84
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
85
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
86
+ "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
87
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
88
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
92
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
94
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
95
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
96
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
97
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
98
+ "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
99
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
104
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
118
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
122
+ "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
150
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
152
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
217
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
218
+ "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
219
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
222
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
223
+ "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
224
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
242
+ "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
243
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
244
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
245
+ "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
246
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
247
+ "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
248
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
249
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
250
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
251
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
253
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
254
+ "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
255
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
257
+ "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
258
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
259
+ "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
260
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
261
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
267
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
296
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
298
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
300
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
302
+ "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
303
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
304
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
306
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
307
+ "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
308
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
310
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
314
+ "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
315
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
318
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
320
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
322
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
324
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
326
+ "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
327
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
328
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
329
+ "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
330
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
331
+ "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
332
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
333
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
334
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
335
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
336
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
337
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
339
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
340
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
341
+ "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
342
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
344
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin",
346
+ "visual.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
347
+ "visual.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
348
+ "visual.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
349
+ "visual.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
350
+ "visual.blocks.0.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
351
+ "visual.blocks.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
354
+ "visual.blocks.0.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
355
+ "visual.blocks.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
356
+ "visual.blocks.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
357
+ "visual.blocks.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
358
+ "visual.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
359
+ "visual.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
360
+ "visual.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
361
+ "visual.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
362
+ "visual.blocks.1.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
363
+ "visual.blocks.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
366
+ "visual.blocks.1.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
367
+ "visual.blocks.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
368
+ "visual.blocks.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
369
+ "visual.blocks.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
370
+ "visual.blocks.10.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
371
+ "visual.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
372
+ "visual.blocks.10.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
373
+ "visual.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
374
+ "visual.blocks.10.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
375
+ "visual.blocks.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
378
+ "visual.blocks.10.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
379
+ "visual.blocks.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "visual.blocks.10.norm1.weight": "pytorch_model-00001-of-00002.bin",
381
+ "visual.blocks.10.norm2.weight": "pytorch_model-00001-of-00002.bin",
382
+ "visual.blocks.11.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
383
+ "visual.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
384
+ "visual.blocks.11.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
385
+ "visual.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
386
+ "visual.blocks.11.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
387
+ "visual.blocks.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "visual.blocks.11.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
391
+ "visual.blocks.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
392
+ "visual.blocks.11.norm1.weight": "pytorch_model-00001-of-00002.bin",
393
+ "visual.blocks.11.norm2.weight": "pytorch_model-00001-of-00002.bin",
394
+ "visual.blocks.12.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
395
+ "visual.blocks.12.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "visual.blocks.12.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
397
+ "visual.blocks.12.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
398
+ "visual.blocks.12.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
399
+ "visual.blocks.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
402
+ "visual.blocks.12.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
403
+ "visual.blocks.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
404
+ "visual.blocks.12.norm1.weight": "pytorch_model-00001-of-00002.bin",
405
+ "visual.blocks.12.norm2.weight": "pytorch_model-00001-of-00002.bin",
406
+ "visual.blocks.13.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
407
+ "visual.blocks.13.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
408
+ "visual.blocks.13.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
409
+ "visual.blocks.13.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
410
+ "visual.blocks.13.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
411
+ "visual.blocks.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
414
+ "visual.blocks.13.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
415
+ "visual.blocks.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "visual.blocks.13.norm1.weight": "pytorch_model-00001-of-00002.bin",
417
+ "visual.blocks.13.norm2.weight": "pytorch_model-00001-of-00002.bin",
418
+ "visual.blocks.14.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
419
+ "visual.blocks.14.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
420
+ "visual.blocks.14.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
421
+ "visual.blocks.14.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
422
+ "visual.blocks.14.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
423
+ "visual.blocks.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
426
+ "visual.blocks.14.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
427
+ "visual.blocks.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
428
+ "visual.blocks.14.norm1.weight": "pytorch_model-00001-of-00002.bin",
429
+ "visual.blocks.14.norm2.weight": "pytorch_model-00001-of-00002.bin",
430
+ "visual.blocks.15.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
431
+ "visual.blocks.15.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
432
+ "visual.blocks.15.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
433
+ "visual.blocks.15.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
434
+ "visual.blocks.15.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
435
+ "visual.blocks.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
438
+ "visual.blocks.15.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
439
+ "visual.blocks.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "visual.blocks.15.norm1.weight": "pytorch_model-00001-of-00002.bin",
441
+ "visual.blocks.15.norm2.weight": "pytorch_model-00001-of-00002.bin",
442
+ "visual.blocks.16.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
443
+ "visual.blocks.16.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
444
+ "visual.blocks.16.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
445
+ "visual.blocks.16.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
446
+ "visual.blocks.16.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
447
+ "visual.blocks.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
450
+ "visual.blocks.16.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
451
+ "visual.blocks.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
452
+ "visual.blocks.16.norm1.weight": "pytorch_model-00001-of-00002.bin",
453
+ "visual.blocks.16.norm2.weight": "pytorch_model-00001-of-00002.bin",
454
+ "visual.blocks.17.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
455
+ "visual.blocks.17.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
456
+ "visual.blocks.17.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
457
+ "visual.blocks.17.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
458
+ "visual.blocks.17.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
459
+ "visual.blocks.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
462
+ "visual.blocks.17.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
463
+ "visual.blocks.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
464
+ "visual.blocks.17.norm1.weight": "pytorch_model-00001-of-00002.bin",
465
+ "visual.blocks.17.norm2.weight": "pytorch_model-00001-of-00002.bin",
466
+ "visual.blocks.18.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
467
+ "visual.blocks.18.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
468
+ "visual.blocks.18.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
469
+ "visual.blocks.18.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
470
+ "visual.blocks.18.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
471
+ "visual.blocks.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
474
+ "visual.blocks.18.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
475
+ "visual.blocks.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "visual.blocks.18.norm1.weight": "pytorch_model-00001-of-00002.bin",
477
+ "visual.blocks.18.norm2.weight": "pytorch_model-00001-of-00002.bin",
478
+ "visual.blocks.19.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
479
+ "visual.blocks.19.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
480
+ "visual.blocks.19.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
481
+ "visual.blocks.19.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
482
+ "visual.blocks.19.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
483
+ "visual.blocks.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
486
+ "visual.blocks.19.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
487
+ "visual.blocks.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
488
+ "visual.blocks.19.norm1.weight": "pytorch_model-00001-of-00002.bin",
489
+ "visual.blocks.19.norm2.weight": "pytorch_model-00001-of-00002.bin",
490
+ "visual.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
491
+ "visual.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
492
+ "visual.blocks.2.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
493
+ "visual.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
494
+ "visual.blocks.2.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
495
+ "visual.blocks.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
498
+ "visual.blocks.2.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
499
+ "visual.blocks.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
500
+ "visual.blocks.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
501
+ "visual.blocks.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
502
+ "visual.blocks.20.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
503
+ "visual.blocks.20.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
504
+ "visual.blocks.20.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
505
+ "visual.blocks.20.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
506
+ "visual.blocks.20.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
507
+ "visual.blocks.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
510
+ "visual.blocks.20.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
511
+ "visual.blocks.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
512
+ "visual.blocks.20.norm1.weight": "pytorch_model-00001-of-00002.bin",
513
+ "visual.blocks.20.norm2.weight": "pytorch_model-00001-of-00002.bin",
514
+ "visual.blocks.21.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
515
+ "visual.blocks.21.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
516
+ "visual.blocks.21.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
517
+ "visual.blocks.21.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
518
+ "visual.blocks.21.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
519
+ "visual.blocks.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
522
+ "visual.blocks.21.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
523
+ "visual.blocks.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
524
+ "visual.blocks.21.norm1.weight": "pytorch_model-00001-of-00002.bin",
525
+ "visual.blocks.21.norm2.weight": "pytorch_model-00001-of-00002.bin",
526
+ "visual.blocks.22.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
527
+ "visual.blocks.22.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
528
+ "visual.blocks.22.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
529
+ "visual.blocks.22.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
530
+ "visual.blocks.22.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
531
+ "visual.blocks.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
534
+ "visual.blocks.22.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
535
+ "visual.blocks.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
536
+ "visual.blocks.22.norm1.weight": "pytorch_model-00001-of-00002.bin",
537
+ "visual.blocks.22.norm2.weight": "pytorch_model-00001-of-00002.bin",
538
+ "visual.blocks.23.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
539
+ "visual.blocks.23.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
540
+ "visual.blocks.23.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
541
+ "visual.blocks.23.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
542
+ "visual.blocks.23.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
543
+ "visual.blocks.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
546
+ "visual.blocks.23.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
547
+ "visual.blocks.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
548
+ "visual.blocks.23.norm1.weight": "pytorch_model-00001-of-00002.bin",
549
+ "visual.blocks.23.norm2.weight": "pytorch_model-00001-of-00002.bin",
550
+ "visual.blocks.24.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
551
+ "visual.blocks.24.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
552
+ "visual.blocks.24.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
553
+ "visual.blocks.24.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
554
+ "visual.blocks.24.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
555
+ "visual.blocks.24.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
558
+ "visual.blocks.24.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
559
+ "visual.blocks.24.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
560
+ "visual.blocks.24.norm1.weight": "pytorch_model-00001-of-00002.bin",
561
+ "visual.blocks.24.norm2.weight": "pytorch_model-00001-of-00002.bin",
562
+ "visual.blocks.25.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
563
+ "visual.blocks.25.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
564
+ "visual.blocks.25.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
565
+ "visual.blocks.25.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
566
+ "visual.blocks.25.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
567
+ "visual.blocks.25.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
570
+ "visual.blocks.25.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
571
+ "visual.blocks.25.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
572
+ "visual.blocks.25.norm1.weight": "pytorch_model-00001-of-00002.bin",
573
+ "visual.blocks.25.norm2.weight": "pytorch_model-00001-of-00002.bin",
574
+ "visual.blocks.26.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
575
+ "visual.blocks.26.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
576
+ "visual.blocks.26.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
577
+ "visual.blocks.26.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
578
+ "visual.blocks.26.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
579
+ "visual.blocks.26.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
582
+ "visual.blocks.26.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
583
+ "visual.blocks.26.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
584
+ "visual.blocks.26.norm1.weight": "pytorch_model-00001-of-00002.bin",
585
+ "visual.blocks.26.norm2.weight": "pytorch_model-00001-of-00002.bin",
586
+ "visual.blocks.27.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
587
+ "visual.blocks.27.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
588
+ "visual.blocks.27.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
589
+ "visual.blocks.27.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
590
+ "visual.blocks.27.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
591
+ "visual.blocks.27.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
594
+ "visual.blocks.27.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
595
+ "visual.blocks.27.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
596
+ "visual.blocks.27.norm1.weight": "pytorch_model-00001-of-00002.bin",
597
+ "visual.blocks.27.norm2.weight": "pytorch_model-00001-of-00002.bin",
598
+ "visual.blocks.28.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
599
+ "visual.blocks.28.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
600
+ "visual.blocks.28.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
601
+ "visual.blocks.28.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
602
+ "visual.blocks.28.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
603
+ "visual.blocks.28.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
606
+ "visual.blocks.28.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
607
+ "visual.blocks.28.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
608
+ "visual.blocks.28.norm1.weight": "pytorch_model-00001-of-00002.bin",
609
+ "visual.blocks.28.norm2.weight": "pytorch_model-00001-of-00002.bin",
610
+ "visual.blocks.29.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
611
+ "visual.blocks.29.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
612
+ "visual.blocks.29.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
613
+ "visual.blocks.29.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
614
+ "visual.blocks.29.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
615
+ "visual.blocks.29.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
618
+ "visual.blocks.29.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
619
+ "visual.blocks.29.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
620
+ "visual.blocks.29.norm1.weight": "pytorch_model-00001-of-00002.bin",
621
+ "visual.blocks.29.norm2.weight": "pytorch_model-00001-of-00002.bin",
622
+ "visual.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
623
+ "visual.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
624
+ "visual.blocks.3.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
625
+ "visual.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
626
+ "visual.blocks.3.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
627
+ "visual.blocks.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
630
+ "visual.blocks.3.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
631
+ "visual.blocks.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
632
+ "visual.blocks.3.norm1.weight": "pytorch_model-00001-of-00002.bin",
633
+ "visual.blocks.3.norm2.weight": "pytorch_model-00001-of-00002.bin",
634
+ "visual.blocks.30.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
635
+ "visual.blocks.30.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
636
+ "visual.blocks.30.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
637
+ "visual.blocks.30.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
638
+ "visual.blocks.30.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
639
+ "visual.blocks.30.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
642
+ "visual.blocks.30.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
643
+ "visual.blocks.30.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
644
+ "visual.blocks.30.norm1.weight": "pytorch_model-00001-of-00002.bin",
645
+ "visual.blocks.30.norm2.weight": "pytorch_model-00001-of-00002.bin",
646
+ "visual.blocks.31.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
647
+ "visual.blocks.31.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
648
+ "visual.blocks.31.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
649
+ "visual.blocks.31.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
650
+ "visual.blocks.31.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
651
+ "visual.blocks.31.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
654
+ "visual.blocks.31.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
655
+ "visual.blocks.31.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
656
+ "visual.blocks.31.norm1.weight": "pytorch_model-00001-of-00002.bin",
657
+ "visual.blocks.31.norm2.weight": "pytorch_model-00001-of-00002.bin",
658
+ "visual.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
659
+ "visual.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
660
+ "visual.blocks.4.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
661
+ "visual.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
662
+ "visual.blocks.4.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
663
+ "visual.blocks.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
666
+ "visual.blocks.4.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
667
+ "visual.blocks.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
668
+ "visual.blocks.4.norm1.weight": "pytorch_model-00001-of-00002.bin",
669
+ "visual.blocks.4.norm2.weight": "pytorch_model-00001-of-00002.bin",
670
+ "visual.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
671
+ "visual.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
672
+ "visual.blocks.5.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
673
+ "visual.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
674
+ "visual.blocks.5.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
675
+ "visual.blocks.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
678
+ "visual.blocks.5.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
679
+ "visual.blocks.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
680
+ "visual.blocks.5.norm1.weight": "pytorch_model-00001-of-00002.bin",
681
+ "visual.blocks.5.norm2.weight": "pytorch_model-00001-of-00002.bin",
682
+ "visual.blocks.6.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
683
+ "visual.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
684
+ "visual.blocks.6.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
685
+ "visual.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
686
+ "visual.blocks.6.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
687
+ "visual.blocks.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
690
+ "visual.blocks.6.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
691
+ "visual.blocks.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
692
+ "visual.blocks.6.norm1.weight": "pytorch_model-00001-of-00002.bin",
693
+ "visual.blocks.6.norm2.weight": "pytorch_model-00001-of-00002.bin",
694
+ "visual.blocks.7.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
695
+ "visual.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
696
+ "visual.blocks.7.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
697
+ "visual.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
698
+ "visual.blocks.7.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
699
+ "visual.blocks.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
702
+ "visual.blocks.7.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
703
+ "visual.blocks.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
704
+ "visual.blocks.7.norm1.weight": "pytorch_model-00001-of-00002.bin",
705
+ "visual.blocks.7.norm2.weight": "pytorch_model-00001-of-00002.bin",
706
+ "visual.blocks.8.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
707
+ "visual.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
708
+ "visual.blocks.8.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
709
+ "visual.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
710
+ "visual.blocks.8.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
711
+ "visual.blocks.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
714
+ "visual.blocks.8.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
715
+ "visual.blocks.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
716
+ "visual.blocks.8.norm1.weight": "pytorch_model-00001-of-00002.bin",
717
+ "visual.blocks.8.norm2.weight": "pytorch_model-00001-of-00002.bin",
718
+ "visual.blocks.9.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
719
+ "visual.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
720
+ "visual.blocks.9.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
721
+ "visual.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
722
+ "visual.blocks.9.mlp.down_proj.bias": "pytorch_model-00001-of-00002.bin",
723
+ "visual.blocks.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "pytorch_model-00001-of-00002.bin",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
726
+ "visual.blocks.9.mlp.up_proj.bias": "pytorch_model-00001-of-00002.bin",
727
+ "visual.blocks.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
728
+ "visual.blocks.9.norm1.weight": "pytorch_model-00001-of-00002.bin",
729
+ "visual.blocks.9.norm2.weight": "pytorch_model-00001-of-00002.bin",
730
+ "visual.merger.ln_q.weight": "pytorch_model-00001-of-00002.bin",
731
+ "visual.merger.mlp.0.bias": "pytorch_model-00001-of-00002.bin",
732
+ "visual.merger.mlp.0.weight": "pytorch_model-00001-of-00002.bin",
733
+ "visual.merger.mlp.2.bias": "pytorch_model-00001-of-00002.bin",
734
+ "visual.merger.mlp.2.weight": "pytorch_model-00001-of-00002.bin",
735
+ "visual.patch_embed.proj.weight": "pytorch_model-00001-of-00002.bin"
736
+ }
737
+ }
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/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/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
transformer/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "QwenImageTransformer2DModel",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "/workspace/.cache/huggingface/hub/models--Qwen--Qwen-Image-2512/snapshots/25468b98e3276ca6700de15c6628e51b7de54a26/transformer",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 3584,
14
+ "num_attention_heads": 24,
15
+ "num_layers": 60,
16
+ "out_channels": 16,
17
+ "patch_size": 2,
18
+ "quantization_config": {
19
+ "modules_to_not_convert": null,
20
+ "quant_method": "torchao",
21
+ "quant_type": {
22
+ "default": {
23
+ "_data": {
24
+ "set_inductor_config": true,
25
+ "weight_dtype": {
26
+ "_data": "float8_e4m3fn",
27
+ "_type": "torch.dtype"
28
+ }
29
+ },
30
+ "_type": "Float8WeightOnlyConfig",
31
+ "_version": 2
32
+ }
33
+ },
34
+ "quant_type_kwargs": {}
35
+ },
36
+ "use_additional_t_cond": false,
37
+ "use_layer3d_rope": false,
38
+ "zero_cond_t": false
39
+ }
transformer/diffusion_pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6719f9be0d7e60fafe1f81db0eea2b2ca794a24ec0dc3915ab74e99409819974
3
+ size 9994548439
transformer/diffusion_pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04850ed5485cdfb2a25ffd099e548ae7fea5d784d1cac90faad065785d50cf3
3
+ size 9972976343
transformer/diffusion_pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6e2d228f652c646c5eec66c8467e06c9fa7851daa5e791fceff7a60fb1e2cc
3
+ size 491749001
transformer/diffusion_pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLQwenImage",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "_name_or_path": "/workspace/.cache/huggingface/hub/models--Qwen--Qwen-Image-2512/snapshots/25468b98e3276ca6700de15c6628e51b7de54a26/vae",
5
+ "attn_scales": [],
6
+ "base_dim": 96,
7
+ "dim_mult": [
8
+ 1,
9
+ 2,
10
+ 4,
11
+ 4
12
+ ],
13
+ "dropout": 0.0,
14
+ "input_channels": 3,
15
+ "latents_mean": [
16
+ -0.7571,
17
+ -0.7089,
18
+ -0.9113,
19
+ 0.1075,
20
+ -0.1745,
21
+ 0.9653,
22
+ -0.1517,
23
+ 1.5508,
24
+ 0.4134,
25
+ -0.0715,
26
+ 0.5517,
27
+ -0.3632,
28
+ -0.1922,
29
+ -0.9497,
30
+ 0.2503,
31
+ -0.2921
32
+ ],
33
+ "latents_std": [
34
+ 2.8184,
35
+ 1.4541,
36
+ 2.3275,
37
+ 2.6558,
38
+ 1.2196,
39
+ 1.7708,
40
+ 2.6052,
41
+ 2.0743,
42
+ 3.2687,
43
+ 2.1526,
44
+ 2.8652,
45
+ 1.5579,
46
+ 1.6382,
47
+ 1.1253,
48
+ 2.8251,
49
+ 1.916
50
+ ],
51
+ "num_res_blocks": 2,
52
+ "temperal_downsample": [
53
+ false,
54
+ true,
55
+ true
56
+ ],
57
+ "z_dim": 16
58
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd312958e5cdd8ecdc904213216516da5ff9ff970565fb7621d44a68ccd8bea1
3
+ size 253853883