Hugging Face's logo

MerlinSafety
/
Pluto

Image-Text-to-Text
Safetensors
GGUF
English
qwen3_5
code
reasoning
distillation
reinforcement-learning
long-context
claude-code
openai-codex
quantum-entropy
merlin-research
conversational
Model card Files
xet
 Community
squ11z1 commited on
Commit
98e18d7
·
verified ·
1 Parent(s): 3b78e4f

Delete merged

Browse files
Files changed (12) hide show
  1. merged/README.md +0 -24
  2. merged/chat_template.jinja +0 -154
  3. merged/config.json +0 -109
  4. merged/generation_config.json +0 -6
  5. merged/model-00001-of-00004.safetensors +0 -3
  6. merged/model-00002-of-00004.safetensors +0 -3
  7. merged/model-00003-of-00004.safetensors +0 -3
  8. merged/model-00004-of-00004.safetensors +0 -3
  9. merged/model.safetensors.index.json +0 -768
  10. merged/processor_config.json +0 -60
  11. merged/tokenizer.json +0 -3
  12. merged/tokenizer_config.json +0 -32
merged/README.md DELETED
@@ -1,24 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- base_model: Qwen/Qwen3.5-9B-Base
4
- tags:
5
- - qwen3_5
6
- - lora
7
- - reasoning
8
- - merlin-research
9
- - pluto
10
- - quantum-entropy
11
- ---
12
-
13
- # MerlinSafety/Pluto-Qwen3.5-9B
14
-
15
- This repository contains the **merged full model** artifact for **Pluto**, a personalized Qwen3.5-9B model by **Merlin Research**.
16
-
17
- Training notes:
18
-
19
- - Base model: `Qwen/Qwen3.5-9B-Base`
20
- - Personalization: the model is instructed and reinforced to identify itself as **Pluto** by **Merlin Research**
21
- - Training data: local `messages` SFT dataset
22
- - Quantum entropy usage: raw IBM quantum bitstrings were used as a stochastic source for seeds, dataset shuffle, split, and crop jitter
23
-
24
- This entropy source was used as an external stochastic controller, not as fake supervised labels.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merged/chat_template.jinja DELETED
@@ -1,154 +0,0 @@
1
- {%- set image_count = namespace(value=0) %}
2
- {%- set video_count = namespace(value=0) %}
3
- {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
- {%- if content is string %}
5
- {{- content }}
6
- {%- elif content is iterable and content is not mapping %}
7
- {%- for item in content %}
8
- {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
- {%- if is_system_content %}
10
- {{- raise_exception('System message cannot contain images.') }}
11
- {%- endif %}
12
- {%- if do_vision_count %}
13
- {%- set image_count.value = image_count.value + 1 %}
14
- {%- endif %}
15
- {%- if add_vision_id %}
16
- {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
- {%- endif %}
18
- {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
- {%- elif 'video' in item or item.type == 'video' %}
20
- {%- if is_system_content %}
21
- {{- raise_exception('System message cannot contain videos.') }}
22
- {%- endif %}
23
- {%- if do_vision_count %}
24
- {%- set video_count.value = video_count.value + 1 %}
25
- {%- endif %}
26
- {%- if add_vision_id %}
27
- {{- 'Video ' ~ video_count.value ~ ': ' }}
28
- {%- endif %}
29
- {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
- {%- elif 'text' in item %}
31
- {{- item.text }}
32
- {%- else %}
33
- {{- raise_exception('Unexpected item type in content.') }}
34
- {%- endif %}
35
- {%- endfor %}
36
- {%- elif content is none or content is undefined %}
37
- {{- '' }}
38
- {%- else %}
39
- {{- raise_exception('Unexpected content type.') }}
40
- {%- endif %}
41
- {%- endmacro %}
42
- {%- if not messages %}
43
- {{- raise_exception('No messages provided.') }}
44
- {%- endif %}
45
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if loop.index0 > ns.last_query_index %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merged/config.json DELETED
@@ -1,109 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "dtype": "bfloat16",
6
- "image_token_id": 248056,
7
- "model_type": "qwen3_5",
8
- "text_config": {
9
- "attention_bias": false,
10
- "attention_dropout": 0.0,
11
- "attn_output_gate": true,
12
- "bos_token_id": null,
13
- "dtype": "bfloat16",
14
- "eos_token_id": 248044,
15
- "full_attention_interval": 4,
16
- "head_dim": 256,
17
- "hidden_act": "silu",
18
- "hidden_size": 4096,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 12288,
21
- "layer_types": [
22
- "linear_attention",
23
- "linear_attention",
24
- "linear_attention",
25
- "full_attention",
26
- "linear_attention",
27
- "linear_attention",
28
- "linear_attention",
29
- "full_attention",
30
- "linear_attention",
31
- "linear_attention",
32
- "linear_attention",
33
- "full_attention",
34
- "linear_attention",
35
- "linear_attention",
36
- "linear_attention",
37
- "full_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "linear_attention",
41
- "full_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "linear_attention",
45
- "full_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "linear_attention",
49
- "full_attention",
50
- "linear_attention",
51
- "linear_attention",
52
- "linear_attention",
53
- "full_attention"
54
- ],
55
- "linear_conv_kernel_dim": 4,
56
- "linear_key_head_dim": 128,
57
- "linear_num_key_heads": 16,
58
- "linear_num_value_heads": 32,
59
- "linear_value_head_dim": 128,
60
- "mamba_ssm_dtype": "float32",
61
- "max_position_embeddings": 262144,
62
- "mlp_only_layers": [],
63
- "model_type": "qwen3_5_text",
64
- "mtp_num_hidden_layers": 1,
65
- "mtp_use_dedicated_embeddings": false,
66
- "num_attention_heads": 16,
67
- "num_hidden_layers": 32,
68
- "num_key_value_heads": 4,
69
- "pad_token_id": null,
70
- "partial_rotary_factor": 0.25,
71
- "rms_norm_eps": 1e-06,
72
- "rope_parameters": {
73
- "mrope_interleaved": true,
74
- "mrope_section": [
75
- 11,
76
- 11,
77
- 10
78
- ],
79
- "partial_rotary_factor": 0.25,
80
- "rope_theta": 10000000,
81
- "rope_type": "default"
82
- },
83
- "tie_word_embeddings": false,
84
- "use_cache": true,
85
- "vocab_size": 248320
86
- },
87
- "tie_word_embeddings": false,
88
- "transformers_version": "5.3.0.dev0",
89
- "video_token_id": 248057,
90
- "vision_config": {
91
- "deepstack_visual_indexes": [],
92
- "depth": 27,
93
- "dtype": "bfloat16",
94
- "hidden_act": "gelu_pytorch_tanh",
95
- "hidden_size": 1152,
96
- "in_channels": 3,
97
- "initializer_range": 0.02,
98
- "intermediate_size": 4304,
99
- "model_type": "qwen3_5",
100
- "num_heads": 16,
101
- "num_position_embeddings": 2304,
102
- "out_hidden_size": 4096,
103
- "patch_size": 16,
104
- "spatial_merge_size": 2,
105
- "temporal_patch_size": 2
106
- },
107
- "vision_end_token_id": 248054,
108
- "vision_start_token_id": 248053
109
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merged/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": 248044,
4
- "transformers_version": "5.3.0.dev0",
5
- "use_cache": true
6
- }
 
 
 
 
 
 
 
merged/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c3df59e38b91618a80aa7f76d8eca819b7d672ed465169906349208bdfe5f8b
3
- size 4942706120
 
 
 
 
merged/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13702e09da2cc1132d79c90160b6b86e080372f5cb067b5a6d39f9386a18f14c
3
- size 4987757928
 
 
 
 
merged/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:654b4a7d60738df87f6e86842d6a9eeabbf1f0ec9960de83af7de4b67c323584
3
- size 4954810240
 
 
 
 
merged/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba2ae80deb0e96af81f43c3a91798af09d522dd5430d496f92a7d0bcbfb6b50a
3
- size 3934446832
 
 
 
 
merged/model.safetensors.index.json DELETED
@@ -1,768 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 9409813744,
4
- "total_size": 18819627488
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
- }
768
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merged/processor_config.json DELETED
@@ -1,60 +0,0 @@
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": 234881024,
55
- "shortest_edge": 4096
56
- },
57
- "temporal_patch_size": 2,
58
- "video_processor_type": "Qwen3VLVideoProcessor"
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merged/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
- size 19989343
 
 
 
 
merged/tokenizer_config.json DELETED
@@ -1,32 +0,0 @@
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
- "clean_up_tokenization_spaces": false,
9
- "eos_token": "<|endoftext|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": false,
13
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|endoftext|>",
24
- "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+",
25
- "processor_class": "Qwen3VLProcessor",
26
- "split_special_tokens": false,
27
- "tokenizer_class": "TokenizersBackend",
28
- "unk_token": null,
29
- "video_token": "<|video_pad|>",
30
- "vision_bos_token": "<|vision_start|>",
31
- "vision_eos_token": "<|vision_end|>"
32
- }