Hugging Face's logo

SL-AI
/
GRaPE-2.5-Helios

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
thinking_modes
qwen3.5
grape
vision
multimodal
instruct
chat
coding
math
science
reasoning
creative_writing
roleplay
conversational
Model card Files
xet
 Community
Sweaterdog commited on
Commit
cd7a521
·
verified ·
1 Parent(s): 812d098

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +4 -0
  2. chat_template.jinja +171 -0
  3. config.json +144 -0
  4. generation_config.json +9 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model-mtp.safetensors +3 -0
  10. model.safetensors.index.json +783 -0
  11. preprocessor_config.json +21 -0
  12. processor_config.json +60 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +34 -0
  15. video_preprocessor_config.json +21 -0
  16. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ assets/ornith_397b_eval.png filter=lfs diff=lfs merge=lfs -text
37
+ assets/ornith_9b_eval.png filter=lfs diff=lfs merge=lfs -text
38
+ assets/ornith_logo.png filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
4
+ {%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
5
+ {%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}
6
+ {%- set ns_state = namespace(thinking=enable_thinking) %}
7
+
8
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
9
+ {%- if content is string %}
10
+ {{- content }}
11
+ {%- elif content is iterable and content is not mapping %}
12
+ {%- for item in content %}
13
+ {%- if item is mapping %}
14
+ {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
15
+ {%- if is_system_content %}
16
+ {{- raise_exception('System message cannot contain images.') }}
17
+ {%- endif %}
18
+ {%- if do_vision_count %}
19
+ {%- set image_count.value = image_count.value + 1 %}
20
+ {%- endif %}
21
+ {%- if add_vision_id %}
22
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
23
+ {%- endif %}
24
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
25
+ {%- elif item.type == 'video' or 'video' in item %}
26
+ {%- if is_system_content %}
27
+ {{- raise_exception('System message cannot contain videos.') }}
28
+ {%- endif %}
29
+ {%- if do_vision_count %}
30
+ {%- set video_count.value = video_count.value + 1 %}
31
+ {%- endif %}
32
+ {%- if add_vision_id %}
33
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
34
+ {%- endif %}
35
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
36
+ {%- elif 'text' in item %}
37
+ {{- item.text }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected item type in content.') }}
40
+ {%- endif %}
41
+ {%- else %}
42
+ {{- item | string }}
43
+ {%- endif %}
44
+ {%- endfor %}
45
+ {%- elif content is none or content is undefined %}
46
+ {{- '' }}
47
+ {%- else %}
48
+ {{- raise_exception('Unexpected content type.') }}
49
+ {%- endif %}
50
+ {%- endmacro %}
51
+
52
+ {%- if not messages %}
53
+ {{- raise_exception('No messages provided.') }}
54
+ {%- endif %}
55
+
56
+ {%- set _first_role = messages[0].role %}
57
+ {%- if _first_role == 'system' or _first_role == 'developer' %}
58
+ {%- set _sys_msg = messages[0] %}
59
+ {%- set _msgs = messages[1:] %}
60
+ {%- else %}
61
+ {%- set _sys_msg = none %}
62
+ {%- set _msgs = messages %}
63
+ {%- endif %}
64
+
65
+ {%- set _sc = '' %}
66
+ {%- if _sys_msg is not none %}
67
+ {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}
68
+ {%- endif %}
69
+
70
+ {%- if _sc %}
71
+ {{- '<|im_start|>system\n' + _sc + '<|im_end|>\n' }}
72
+ {%- endif %}
73
+
74
+ {%- set _last_idx = _msgs | length - 1 %}
75
+ {%- set ns = namespace(last_query_index=_last_idx) %}
76
+
77
+ {%- for message in _msgs[::-1] %}
78
+ {%- set index = (_msgs | length - 1) - loop.index0 %}
79
+ {%- if message.role == 'user' %}
80
+ {%- set ns.last_query_index = index %}
81
+ {%- break %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+
85
+ {%- for message in _msgs %}
86
+ {%- set is_system = (message.role == "system" or message.role == "developer") %}
87
+ {%- set content = render_content(message.content, true, is_system) | trim %}
88
+
89
+ {%- if is_system or message.role == 'user' %}
90
+ {%- if '<|think_off|>' in content %}
91
+ {%- set ns_state.thinking = false %}
92
+ {%- set content = content.split('<|think_off|>') | join('') | trim %}
93
+ {%- elif '<|think_on|>' in content %}
94
+ {%- set ns_state.thinking = true %}
95
+ {%- set content = content.split('<|think_on|>') | join('') | trim %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+
99
+ {%- if is_system %}
100
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
101
+
102
+ {%- elif message.role == 'user' %}
103
+ {{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
104
+
105
+ {%- elif message.role == 'assistant' %}
106
+ {%- set reasoning_content = '' %}
107
+
108
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
109
+ {%- if message.reasoning_content is string %}
110
+ {%- set reasoning_content = message.reasoning_content %}
111
+ {%- else %}
112
+ {%- set reasoning_content = message.reasoning_content | string %}
113
+ {%- endif %}
114
+
115
+ {%- elif message.thinking is defined and message.thinking is not none %}
116
+ {%- if message.thinking is string %}
117
+ {%- set reasoning_content = message.thinking %}
118
+ {%- else %}
119
+ {%- set reasoning_content = message.thinking | string %}
120
+ {%- endif %}
121
+
122
+ {%- else %}
123
+ {%- set _think_end = '' %}
124
+
125
+ {%- if content.startswith('</think>') %}
126
+ {%- set _think_end = '</think>' %}
127
+ {%- elif content.startswith('</thinking>') %}
128
+ {%- set _think_end = '</thinking>' %}
129
+ {%- elif '\n</think>' in content %}
130
+ {%- set _think_end = '\n</think>' %}
131
+ {%- elif '\n</thinking>' in content %}
132
+ {%- set _think_end = '\n</thinking>' %}
133
+ {%- elif '\n</ think>' in content %}
134
+ {%- set _think_end = '\n</ think>' %}
135
+ {%- elif '\n</think >' in content %}
136
+ {%- set _think_end = '\n</think >' %}
137
+ {%- endif %}
138
+
139
+ {%- if _think_end %}
140
+ {%- if 'thinking' in _think_end %}
141
+ {%- set _think_start = '<thinking>' %}
142
+ {%- else %}
143
+ {%- set _think_start = '<think>' %}
144
+ {%- endif %}
145
+
146
+ {%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
147
+
148
+ {%- if _think_start in reasoning_content %}
149
+ {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
150
+ {%- endif %}
151
+
152
+ {%- set content = content.split(_think_end)[-1].lstrip('\n') %}
153
+ {%- endif %}
154
+ {%- endif %}
155
+
156
+ {%- set reasoning_content = reasoning_content | trim %}
157
+
158
+ {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}
159
+ {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content + '<|im_end|>\n' }}
160
+ {%- else %}
161
+ {{- '<|im_start|>assistant\n' + content + '<|im_end|>\n' }}
162
+ {%- endif %}
163
+
164
+ {%- else %}
165
+ {{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
166
+ {%- endif %}
167
+ {%- endfor %}
168
+
169
+ {%- if add_generation_prompt %}
170
+ {{- '<|im_start|>assistant\n' }}
171
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "GRaPE 2.5 Helios step 3700",
3
+ "architectures": [
4
+ "Qwen3_5ForConditionalGeneration"
5
+ ],
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "grape_training": {
9
+ "assistant_only_loss": true,
10
+ "checkpoint_state": {
11
+ "best_eval_nll": 1.1276759576956183,
12
+ "best_step": 3700,
13
+ "dataset_sha256": "2f1dfe69b3a05ade3a5adab1642e81dc225a26c61c7c2881dae7ac312acd711b",
14
+ "evals_without_improvement": 0,
15
+ "lora_module_hash": "6ad13a1fae2d098e",
16
+ "module_hash": "d0b5332f62933afb",
17
+ "started_at": "2026-08-20T23:57:54-0700",
18
+ "step": 3700,
19
+ "tokens": 242483200,
20
+ "trainable_tokens": 140830918
21
+ },
22
+ "checkpoint_step": 3700,
23
+ "context_length": 65536,
24
+ "crt_modules": 2,
25
+ "inherited_lora_checkpoint": "/mnt/Disk 3/models/GRaPE 2.5 Helios/runs/crepe2.5_flash-ornith-1.5-20260820-233549-exl3-4bpw-stable/checkpoint-step-750",
26
+ "inherited_lora_scale": 1.0,
27
+ "inherited_lora_subtracted": 198,
28
+ "lora_modules": 198,
29
+ "lora_scale": 1.0,
30
+ "model_authored_think": true
31
+ },
32
+ "hidden_size": 4096,
33
+ "image_token_id": 248056,
34
+ "model_type": "qwen3_5",
35
+ "mtp_graft": {
36
+ "donor_sha256": "3364927c48260f6f4aa724bb9f9e17cefa5ab5749e443a72da1625db46706a02",
37
+ "reason": "original checkpoint declared MTP but omitted all MTP tensors",
38
+ "source": "Qwen/Qwen3.5-9B",
39
+ "tensor_count": 15
40
+ },
41
+ "pad_token_id": 248044,
42
+ "text_config": {
43
+ "attention_bias": false,
44
+ "attention_dropout": 0.0,
45
+ "attn_output_gate": true,
46
+ "bos_token_id": null,
47
+ "dtype": "bfloat16",
48
+ "eos_token_id": 248044,
49
+ "full_attention_interval": 4,
50
+ "head_dim": 256,
51
+ "hidden_act": "silu",
52
+ "hidden_size": 4096,
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 12288,
55
+ "layer_types": [
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "full_attention"
88
+ ],
89
+ "linear_conv_kernel_dim": 4,
90
+ "linear_key_head_dim": 128,
91
+ "linear_num_key_heads": 16,
92
+ "linear_num_value_heads": 32,
93
+ "linear_value_head_dim": 128,
94
+ "mamba_ssm_dtype": "float32",
95
+ "max_position_embeddings": 262144,
96
+ "mlp_only_layers": [],
97
+ "model_type": "qwen3_5_text",
98
+ "mtp_num_hidden_layers": 1,
99
+ "mtp_use_dedicated_embeddings": false,
100
+ "num_attention_heads": 16,
101
+ "num_hidden_layers": 32,
102
+ "num_key_value_heads": 4,
103
+ "pad_token_id": 248044,
104
+ "partial_rotary_factor": 0.25,
105
+ "rms_norm_eps": 1e-06,
106
+ "rope_parameters": {
107
+ "mrope_interleaved": true,
108
+ "mrope_section": [
109
+ 11,
110
+ 11,
111
+ 10
112
+ ],
113
+ "partial_rotary_factor": 0.25,
114
+ "rope_theta": 10000000,
115
+ "rope_type": "default"
116
+ },
117
+ "tie_word_embeddings": false,
118
+ "use_cache": false,
119
+ "vocab_size": 248320
120
+ },
121
+ "tie_word_embeddings": false,
122
+ "transformers_version": "5.8.1",
123
+ "use_cache": false,
124
+ "video_token_id": 248057,
125
+ "vision_config": {
126
+ "deepstack_visual_indexes": [],
127
+ "depth": 27,
128
+ "dtype": "bfloat16",
129
+ "hidden_act": "gelu_pytorch_tanh",
130
+ "hidden_size": 1152,
131
+ "in_channels": 3,
132
+ "initializer_range": 0.02,
133
+ "intermediate_size": 4304,
134
+ "model_type": "qwen3_5_vision",
135
+ "num_heads": 16,
136
+ "num_position_embeddings": 2304,
137
+ "out_hidden_size": 4096,
138
+ "patch_size": 16,
139
+ "spatial_merge_size": 2,
140
+ "temporal_patch_size": 2
141
+ },
142
+ "vision_end_token_id": 248054,
143
+ "vision_start_token_id": 248053
144
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248044,
5
+ 248046
6
+ ],
7
+ "transformers_version": "5.8.1",
8
+ "use_cache": true
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c7e0a1e27252900d1e5cb59cfbbd0f8fbaa877e8209046bbc0d3e7bd836b5a
3
+ size 4942706120
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3542dadf9ed5fc21eeecde614df7bfb0c77e7c2f8ff2310460b09dbbf17828d7
3
+ size 4987757928
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e82a942c3e7c959d947a0c251e9dfcf9aaccf38f29f22ca3cc4e7fd82d4019
3
+ size 4954810240
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cc190755a9b2d7b5377addd4dec3ee801b40e02806d3abeaf08f20635ba62d
3
+ size 3934446832
model-mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3364927c48260f6f4aa724bb9f9e17cefa5ab5749e443a72da1625db46706a02
3
+ size 486582928
model.safetensors.index.json ADDED
@@ -0,0 +1,783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1469680,
4
+ "total_size": 19306208736
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00004.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
32
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
35
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
36
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
37
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
39
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
40
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
41
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
42
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
43
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
44
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
45
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
46
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
57
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
60
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
64
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
65
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
66
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
67
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
68
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
69
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
70
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
71
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
78
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
79
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
80
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
81
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
82
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
83
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
84
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
85
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
89
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
91
+ "model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
92
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
93
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
94
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
95
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
96
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
97
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
98
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
99
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
102
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
104
+ "model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
110
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
113
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
116
+ "model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
117
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
118
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
119
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
120
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
121
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
122
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
123
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
124
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
131
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
132
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
133
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
134
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
135
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
136
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
137
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
138
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
143
+ "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
145
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
146
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
147
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
148
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
149
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
150
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
151
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
152
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
163
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
166
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
169
+ "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
170
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
171
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
172
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
173
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
174
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
175
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
176
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
177
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
178
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
179
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
180
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
182
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
183
+ "model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
184
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
185
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
186
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
187
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
188
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
189
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
190
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
198
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
199
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
200
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
201
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
202
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
203
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
204
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
212
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
213
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
214
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
215
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
216
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
217
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
218
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
219
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
224
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
230
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
233
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
236
+ "model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
237
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
238
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
239
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
240
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
241
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
242
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
243
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
244
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
251
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
252
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
253
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
254
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
255
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
256
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
257
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
258
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
262
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
263
+ "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
264
+ "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
265
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
266
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
267
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
268
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
269
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
270
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
271
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
272
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
273
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
274
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
275
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
276
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
277
+ "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
278
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
279
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
280
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
281
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
282
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
283
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
284
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
285
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
286
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
287
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
288
+ "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
289
+ "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
290
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
291
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
292
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
293
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
294
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
295
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
296
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
297
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
300
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
301
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
302
+ "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
303
+ "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
304
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
305
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
306
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
307
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
308
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
309
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
310
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
311
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
316
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
317
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
322
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
325
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
326
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
328
+ "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
329
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
330
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
331
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
332
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
333
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
334
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
335
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
336
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
337
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
338
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
341
+ "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
343
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
344
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
345
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
346
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
347
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
348
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
349
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
350
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
351
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
353
+ "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
354
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
355
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
356
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
357
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
358
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
359
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
360
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
361
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
362
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
363
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
364
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
365
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
366
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
367
+ "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
368
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
369
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
370
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
371
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
372
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
373
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
374
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
375
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
376
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
377
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
378
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
379
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
380
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
381
+ "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
382
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
383
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
384
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
385
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
386
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
387
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
388
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
389
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
390
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
391
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
392
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
393
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
394
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
397
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
400
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
401
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
402
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
403
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
404
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
405
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
406
+ "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
407
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
408
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
409
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
410
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
411
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
412
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
413
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
414
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
415
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
416
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
417
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
418
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
419
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
420
+ "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
421
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
422
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
423
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
424
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
425
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
426
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
427
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
428
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
429
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
430
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
431
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
432
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
433
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
434
+ "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
435
+ "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
436
+ "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
437
+ "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
438
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
439
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
440
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
441
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
442
+ "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
443
+ "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
444
+ "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
445
+ "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
446
+ "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
447
+ "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
448
+ "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
449
+ "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
450
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
451
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
452
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
453
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
454
+ "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
455
+ "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
456
+ "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
457
+ "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
458
+ "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
459
+ "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
460
+ "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
461
+ "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
462
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
463
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
464
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
465
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
466
+ "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
467
+ "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
468
+ "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
469
+ "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
470
+ "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
471
+ "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
472
+ "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
473
+ "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
474
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
475
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
476
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
477
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
478
+ "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
479
+ "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
480
+ "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
481
+ "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
482
+ "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
483
+ "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
484
+ "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
485
+ "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
486
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
487
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
488
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
489
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
490
+ "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
491
+ "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
492
+ "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
493
+ "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
494
+ "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
495
+ "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
496
+ "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
497
+ "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
498
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
499
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
500
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
501
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
502
+ "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
503
+ "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
504
+ "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
505
+ "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
506
+ "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
507
+ "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
508
+ "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
509
+ "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
510
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
511
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
512
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
513
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
514
+ "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
515
+ "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
516
+ "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
517
+ "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
518
+ "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
519
+ "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
520
+ "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
521
+ "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
522
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
523
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
524
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
525
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
526
+ "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
527
+ "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
528
+ "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
529
+ "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
530
+ "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
531
+ "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
532
+ "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
533
+ "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
534
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
535
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
536
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
537
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
538
+ "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
539
+ "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
540
+ "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
541
+ "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
542
+ "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
543
+ "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
544
+ "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
545
+ "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
546
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
547
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
548
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
549
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
550
+ "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
551
+ "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
552
+ "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
553
+ "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
554
+ "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
555
+ "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
556
+ "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
557
+ "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
558
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
559
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
560
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
561
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
562
+ "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
563
+ "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
564
+ "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
565
+ "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
566
+ "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
567
+ "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
568
+ "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
569
+ "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
570
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
571
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
572
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
573
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
574
+ "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
575
+ "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
576
+ "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
577
+ "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
578
+ "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
579
+ "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
580
+ "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
581
+ "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
582
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
583
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
584
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
585
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
586
+ "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
587
+ "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
588
+ "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
589
+ "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
590
+ "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
591
+ "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
592
+ "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
593
+ "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
594
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
595
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
596
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
597
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
598
+ "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
599
+ "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
600
+ "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
601
+ "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
602
+ "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
603
+ "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
604
+ "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
605
+ "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
606
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
607
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
608
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
609
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
610
+ "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
611
+ "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
612
+ "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
613
+ "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
614
+ "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
615
+ "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
616
+ "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
617
+ "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
618
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
619
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
620
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
621
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
622
+ "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
623
+ "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
624
+ "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
625
+ "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
626
+ "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
627
+ "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
628
+ "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
629
+ "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
630
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
631
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
632
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
633
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
634
+ "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
635
+ "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
636
+ "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
637
+ "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
638
+ "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
639
+ "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
640
+ "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
641
+ "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
642
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
643
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
644
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
645
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
646
+ "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
647
+ "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
648
+ "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
649
+ "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
650
+ "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
651
+ "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
652
+ "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
653
+ "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
654
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
655
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
656
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
657
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
658
+ "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
659
+ "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
660
+ "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
661
+ "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
662
+ "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
663
+ "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
664
+ "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
665
+ "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
666
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
667
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
668
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
669
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
670
+ "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
671
+ "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
672
+ "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
673
+ "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
674
+ "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
675
+ "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
676
+ "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
677
+ "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
678
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
679
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
680
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
681
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
682
+ "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
683
+ "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
684
+ "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
685
+ "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
686
+ "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
687
+ "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
688
+ "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
689
+ "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
690
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
691
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
692
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
693
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
694
+ "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
695
+ "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
696
+ "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
697
+ "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
698
+ "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
699
+ "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
700
+ "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
701
+ "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
702
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
703
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
704
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
705
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
706
+ "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
707
+ "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
708
+ "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
709
+ "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
710
+ "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
711
+ "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
712
+ "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
713
+ "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
714
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
715
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
716
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
717
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
718
+ "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
719
+ "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
720
+ "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
721
+ "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
722
+ "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
723
+ "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
724
+ "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
725
+ "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
726
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
727
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
728
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
729
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
730
+ "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
731
+ "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
732
+ "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
733
+ "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
734
+ "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
735
+ "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
736
+ "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
737
+ "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
738
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
739
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
740
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
741
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
742
+ "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
743
+ "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
744
+ "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
745
+ "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
746
+ "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
747
+ "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
748
+ "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
749
+ "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
750
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
751
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
752
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
753
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
754
+ "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
755
+ "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
756
+ "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
757
+ "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
758
+ "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
759
+ "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
760
+ "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
761
+ "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
762
+ "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
763
+ "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
764
+ "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
765
+ "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
766
+ "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors",
767
+ "mtp.fc.weight": "model-mtp.safetensors",
768
+ "mtp.layers.0.input_layernorm.weight": "model-mtp.safetensors",
769
+ "mtp.layers.0.mlp.down_proj.weight": "model-mtp.safetensors",
770
+ "mtp.layers.0.mlp.gate_proj.weight": "model-mtp.safetensors",
771
+ "mtp.layers.0.mlp.up_proj.weight": "model-mtp.safetensors",
772
+ "mtp.layers.0.post_attention_layernorm.weight": "model-mtp.safetensors",
773
+ "mtp.layers.0.self_attn.k_norm.weight": "model-mtp.safetensors",
774
+ "mtp.layers.0.self_attn.k_proj.weight": "model-mtp.safetensors",
775
+ "mtp.layers.0.self_attn.o_proj.weight": "model-mtp.safetensors",
776
+ "mtp.layers.0.self_attn.q_norm.weight": "model-mtp.safetensors",
777
+ "mtp.layers.0.self_attn.q_proj.weight": "model-mtp.safetensors",
778
+ "mtp.layers.0.self_attn.v_proj.weight": "model-mtp.safetensors",
779
+ "mtp.norm.weight": "model-mtp.safetensors",
780
+ "mtp.pre_fc_norm_embedding.weight": "model-mtp.safetensors",
781
+ "mtp.pre_fc_norm_hidden.weight": "model-mtp.safetensors"
782
+ }
783
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}\n{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}\n{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}\n{%- set ns_state = namespace(thinking=enable_thinking) %}\n\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if item is mapping %}\n {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif item.type == 'video' or 'video' in item %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- else %}\n {{- item | string }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n\n{%- set _first_role = messages[0].role %}\n{%- if _first_role == 'system' or _first_role == 'developer' %}\n {%- set _sys_msg = messages[0] %}\n {%- set _msgs = messages[1:] %}\n{%- else %}\n {%- set _sys_msg = none %}\n {%- set _msgs = messages %}\n{%- endif %}\n\n{%- set _sc = '' %}\n{%- if _sys_msg is not none %}\n {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}\n{%- endif %}\n\n{%- if _sc %}\n {{- '<|im_start|>system\\n' + _sc + '<|im_end|>\\n' }}\n{%- endif %}\n\n{%- set _last_idx = _msgs | length - 1 %}\n{%- set ns = namespace(last_query_index=_last_idx) %}\n\n{%- for message in _msgs[::-1] %}\n {%- set index = (_msgs | length - 1) - loop.index0 %}\n {%- if message.role == 'user' %}\n {%- set ns.last_query_index = index %}\n {%- break %}\n {%- endif %}\n{%- endfor %}\n\n{%- for message in _msgs %}\n {%- set is_system = (message.role == \"system\" or message.role == \"developer\") %}\n {%- set content = render_content(message.content, true, is_system) | trim %}\n\n {%- if is_system or message.role == 'user' %}\n {%- if '<|think_off|>' in content %}\n {%- set ns_state.thinking = false %}\n {%- set content = content.split('<|think_off|>') | join('') | trim %}\n {%- elif '<|think_on|>' in content %}\n {%- set ns_state.thinking = true %}\n {%- set content = content.split('<|think_on|>') | join('') | trim %}\n {%- endif %}\n {%- endif %}\n\n {%- if is_system %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n\n {%- elif message.role == 'user' %}\n {{- '<|im_start|>user\\n' + content + '<|im_end|>\\n' }}\n\n {%- elif message.role == 'assistant' %}\n {%- set reasoning_content = '' %}\n\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set reasoning_content = message.reasoning_content | string %}\n {%- endif %}\n\n {%- elif message.thinking is defined and message.thinking is not none %}\n {%- if message.thinking is string %}\n {%- set reasoning_content = message.thinking %}\n {%- else %}\n {%- set reasoning_content = message.thinking | string %}\n {%- endif %}\n\n {%- else %}\n {%- set _think_end = '' %}\n\n {%- if content.startswith('</think>') %}\n {%- set _think_end = '</think>' %}\n {%- elif content.startswith('</thinking>') %}\n {%- set _think_end = '</thinking>' %}\n {%- elif '\\n</think>' in content %}\n {%- set _think_end = '\\n</think>' %}\n {%- elif '\\n</thinking>' in content %}\n {%- set _think_end = '\\n</thinking>' %}\n {%- elif '\\n</ think>' in content %}\n {%- set _think_end = '\\n</ think>' %}\n {%- elif '\\n</think >' in content %}\n {%- set _think_end = '\\n</think >' %}\n {%- endif %}\n\n {%- if _think_end %}\n {%- if 'thinking' in _think_end %}\n {%- set _think_start = '<thinking>' %}\n {%- else %}\n {%- set _think_start = '<think>' %}\n {%- endif %}\n\n {%- set reasoning_content = content.split(_think_end)[0].rstrip('\\n') %}\n\n {%- if _think_start in reasoning_content %}\n {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\\n') %}\n {%- endif %}\n\n {%- set content = content.split(_think_end)[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n\n {%- set reasoning_content = reasoning_content | trim %}\n\n {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}\n {{- '<|im_start|>assistant\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>assistant\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n\n {%- else %}\n {{- '<|im_start|>user\\n[' + message.role + ']: ' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
9
+ "clean_up_tokenization_spaces": false,
10
+ "eos_token": "<|im_end|>",
11
+ "errors": "replace",
12
+ "image_token": "<|image_pad|>",
13
+ "is_local": true,
14
+ "local_files_only": false,
15
+ "model_max_length": 262144,
16
+ "model_specific_special_tokens": {
17
+ "audio_bos_token": "<|audio_start|>",
18
+ "audio_eos_token": "<|audio_end|>",
19
+ "audio_token": "<|audio_pad|>",
20
+ "image_token": "<|image_pad|>",
21
+ "video_token": "<|video_pad|>",
22
+ "vision_bos_token": "<|vision_start|>",
23
+ "vision_eos_token": "<|vision_end|>"
24
+ },
25
+ "pad_token": "<|endoftext|>",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff