Hugging Face's logo

dglhf
/
Slonik

Text Generation
Transformers
Safetensors
slonik
code
postgresql
software-engineering
reinforcement-learning
Model card Files
xet
 Community
dglhf commited on
Commit
8825519
·
verified ·
1 Parent(s): 4a95861

Link standalone Slonik models from the shared research overview

Browse files
Files changed (43) hide show
  1. 27B/adapter/adapter_config.json +0 -22
  2. 27B/adapter/adapter_model.safetensors +0 -3
  3. 27B/base/chat_template.jinja +0 -170
  4. 27B/base/config.json +0 -140
  5. 27B/base/generation_config.json +0 -12
  6. 27B/base/merges.txt +0 -0
  7. 27B/base/model-00001-of-00018.safetensors +0 -3
  8. 27B/base/model-00002-of-00018.safetensors +0 -3
  9. 27B/base/model-00003-of-00018.safetensors +0 -3
  10. 27B/base/model-00004-of-00018.safetensors +0 -3
  11. 27B/base/model-00005-of-00018.safetensors +0 -3
  12. 27B/base/model-00006-of-00018.safetensors +0 -3
  13. 27B/base/model-00007-of-00018.safetensors +0 -3
  14. 27B/base/model-00008-of-00018.safetensors +0 -3
  15. 27B/base/model-00009-of-00018.safetensors +0 -3
  16. 27B/base/model-00010-of-00018.safetensors +0 -3
  17. 27B/base/model-00011-of-00018.safetensors +0 -3
  18. 27B/base/model-00012-of-00018.safetensors +0 -3
  19. 27B/base/model-00013-of-00018.safetensors +0 -3
  20. 27B/base/model-00014-of-00018.safetensors +0 -3
  21. 27B/base/model-00015-of-00018.safetensors +0 -3
  22. 27B/base/model-00016-of-00018.safetensors +0 -3
  23. 27B/base/model-00017-of-00018.safetensors +0 -3
  24. 27B/base/model-00018-of-00018.safetensors +0 -3
  25. 27B/base/model.safetensors.index.json +0 -0
  26. 27B/base/preprocessor_config.json +0 -21
  27. 27B/base/tokenizer.json +0 -3
  28. 27B/base/tokenizer_config.json +0 -305
  29. 27B/base/video_preprocessor_config.json +0 -21
  30. 27B/base/vocab.json +0 -0
  31. 9B/chat_template.jinja +0 -154
  32. 9B/config.json +0 -103
  33. 9B/generation_config.json +0 -6
  34. 9B/model-00001-of-00002.safetensors +0 -3
  35. 9B/model-00002-of-00002.safetensors +0 -3
  36. 9B/model.safetensors.index.json +0 -782
  37. 9B/preprocessor_config.json +0 -21
  38. 9B/tokenizer.json +0 -3
  39. 9B/tokenizer_config.json +0 -32
  40. 9B/video_preprocessor_config.json +0 -21
  41. NOTICE +1 -4
  42. README.md +10 -89
  43. checksums.sha256 +0 -40
27B/adapter/adapter_config.json DELETED
@@ -1,22 +0,0 @@
1
- {
2
- "base_model_name_or_path": null,
3
- "peft_type": "LORA",
4
- "task_type": "CAUSAL_LM",
5
- "r": 16,
6
- "lora_alpha": 16,
7
- "target_modules": [
8
- "down_proj",
9
- "gate_proj",
10
- "in_proj_a",
11
- "in_proj_b",
12
- "in_proj_qkv",
13
- "in_proj_z",
14
- "k_proj",
15
- "o_proj",
16
- "out_proj",
17
- "q_proj",
18
- "up_proj",
19
- "v_proj"
20
- ],
21
- "inference_mode": true
22
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/adapter/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b3763b530ac5dd1f4d2d19b1b1765f7cb611b826bab8b6cc456d95a5b1077f
3
- size 233607432
 
 
 
 
27B/base/chat_template.jinja DELETED
@@ -1,170 +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
- {%- set reasoning_instructions = '' %}
46
- {%- if enable_thinking is undefined or enable_thinking is true %}
47
- {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
48
- {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
- {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
- {%- endif %}
51
- {%- if resolved_reasoning_effort == 'xhigh' %}
52
- {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
53
- {%- elif resolved_reasoning_effort == 'low' %}
54
- {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
55
- {%- endif %}
56
- {%- endif %}
57
- {%- if tools and tools is iterable and tools is not mapping %}
58
- {{- '<|im_start|>system\n' }}
59
- {%- if reasoning_instructions %}
60
- {{- reasoning_instructions + '\n\n' }}
61
- {%- endif %}
62
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
- {%- for tool in tools %}
64
- {{- "\n" }}
65
- {{- tool | tojson }}
66
- {%- endfor %}
67
- {{- "\n</tools>" }}
68
- {{- '\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>' }}
69
- {%- if messages[0].role == 'system' %}
70
- {%- set content = render_content(messages[0].content, false, true)|trim %}
71
- {%- if content %}
72
- {{- '\n\n' + content }}
73
- {%- endif %}
74
- {%- endif %}
75
- {{- '<|im_end|>\n' }}
76
- {%- else %}
77
- {%- if messages[0].role == 'system' %}
78
- {%- set content = render_content(messages[0].content, false, true)|trim %}
79
- {%- if content %}
80
- {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
- {%- elif reasoning_instructions %}
82
- {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
- {%- endif %}
84
- {%- elif reasoning_instructions %}
85
- {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
- {%- endif %}
87
- {%- endif %}
88
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
- {%- for message in messages[::-1] %}
90
- {%- set index = (messages|length - 1) - loop.index0 %}
91
- {%- if ns.multi_step_tool and message.role == "user" %}
92
- {%- set content = render_content(message.content, false)|trim %}
93
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
- {%- set ns.multi_step_tool = false %}
95
- {%- set ns.last_query_index = index %}
96
- {%- endif %}
97
- {%- endif %}
98
- {%- endfor %}
99
- {%- if ns.multi_step_tool %}
100
- {{- raise_exception('No user query found in messages.') }}
101
- {%- endif %}
102
- {%- for message in messages %}
103
- {%- set content = render_content(message.content, true)|trim %}
104
- {%- if message.role == "system" %}
105
- {%- if not loop.first %}
106
- {{- raise_exception('System message must be at the beginning.') }}
107
- {%- endif %}
108
- {%- elif message.role == "user" %}
109
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
- {%- elif message.role == "assistant" %}
111
- {%- set reasoning_content = '' %}
112
- {%- if message.reasoning_content is string %}
113
- {%- set reasoning_content = message.reasoning_content %}
114
- {%- endif %}
115
- {%- set reasoning_content = reasoning_content|trim %}
116
- {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
- {%- else %}
119
- {{- '<|im_start|>' + message.role + '\n' + content }}
120
- {%- endif %}
121
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
- {%- for tool_call in message.tool_calls %}
123
- {%- if tool_call.function is defined %}
124
- {%- set tool_call = tool_call.function %}
125
- {%- endif %}
126
- {%- if loop.first %}
127
- {%- if content|trim %}
128
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
- {%- else %}
130
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
- {%- endif %}
132
- {%- else %}
133
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
- {%- endif %}
135
- {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
- {%- for args_name, args_value in tool_call.arguments|items %}
137
- {{- '<parameter=' + args_name + '>\n' }}
138
- {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
- {{- args_value }}
140
- {{- '\n</parameter>\n' }}
141
- {%- endfor %}
142
- {%- endif %}
143
- {{- '</function>\n</tool_call>' }}
144
- {%- endfor %}
145
- {%- endif %}
146
- {{- '<|im_end|>\n' }}
147
- {%- elif message.role == "tool" %}
148
- {%- if loop.previtem and loop.previtem.role != "tool" %}
149
- {{- '<|im_start|>user' }}
150
- {%- endif %}
151
- {{- '\n<tool_response>\n' }}
152
- {{- content }}
153
- {{- '\n</tool_response>' }}
154
- {%- if not loop.last and loop.nextitem.role != "tool" %}
155
- {{- '<|im_end|>\n' }}
156
- {%- elif loop.last %}
157
- {{- '<|im_end|>\n' }}
158
- {%- endif %}
159
- {%- else %}
160
- {{- raise_exception('Unexpected message role.') }}
161
- {%- endif %}
162
- {%- endfor %}
163
- {%- if add_generation_prompt %}
164
- {{- '<|im_start|>assistant\n' }}
165
- {%- if enable_thinking is defined and enable_thinking is false %}
166
- {{- '<think>\n\n</think>\n\n' }}
167
- {%- else %}
168
- {{- '<think>\n' }}
169
- {%- endif %}
170
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/config.json DELETED
@@ -1,140 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "image_token_id": 248056,
6
- "language_model_only": false,
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": 248044,
13
- "dtype": "bfloat16",
14
- "eos_token_id": 248044,
15
- "full_attention_interval": 4,
16
- "head_dim": 256,
17
- "hidden_act": "silu",
18
- "hidden_size": 5120,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 17408,
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
- "linear_attention",
55
- "linear_attention",
56
- "linear_attention",
57
- "full_attention",
58
- "linear_attention",
59
- "linear_attention",
60
- "linear_attention",
61
- "full_attention",
62
- "linear_attention",
63
- "linear_attention",
64
- "linear_attention",
65
- "full_attention",
66
- "linear_attention",
67
- "linear_attention",
68
- "linear_attention",
69
- "full_attention",
70
- "linear_attention",
71
- "linear_attention",
72
- "linear_attention",
73
- "full_attention",
74
- "linear_attention",
75
- "linear_attention",
76
- "linear_attention",
77
- "full_attention",
78
- "linear_attention",
79
- "linear_attention",
80
- "linear_attention",
81
- "full_attention",
82
- "linear_attention",
83
- "linear_attention",
84
- "linear_attention",
85
- "full_attention"
86
- ],
87
- "linear_conv_kernel_dim": 4,
88
- "linear_key_head_dim": 128,
89
- "linear_num_key_heads": 16,
90
- "linear_num_value_heads": 48,
91
- "linear_value_head_dim": 128,
92
- "mamba_ssm_dtype": "float32",
93
- "max_position_embeddings": 262144,
94
- "model_type": "qwen3_5_text",
95
- "mtp_num_hidden_layers": 1,
96
- "mtp_use_dedicated_embeddings": false,
97
- "num_attention_heads": 24,
98
- "num_hidden_layers": 64,
99
- "num_key_value_heads": 4,
100
- "output_gate_type": "swish",
101
- "pad_token_id": null,
102
- "partial_rotary_factor": 0.25,
103
- "rms_norm_eps": 1e-06,
104
- "rope_parameters": {
105
- "mrope_interleaved": true,
106
- "mrope_section": [
107
- 11,
108
- 11,
109
- 10
110
- ],
111
- "partial_rotary_factor": 0.25,
112
- "rope_theta": 10000000,
113
- "rope_type": "default"
114
- },
115
- "tie_word_embeddings": false,
116
- "use_cache": true,
117
- "vocab_size": 248320
118
- },
119
- "tie_word_embeddings": false,
120
- "transformers_version": "5.8.0.dev0",
121
- "video_token_id": 248057,
122
- "vision_config": {
123
- "deepstack_visual_indexes": [],
124
- "depth": 27,
125
- "hidden_act": "gelu_pytorch_tanh",
126
- "hidden_size": 1152,
127
- "in_channels": 3,
128
- "initializer_range": 0.02,
129
- "intermediate_size": 4304,
130
- "model_type": "qwen3_5",
131
- "num_heads": 16,
132
- "num_position_embeddings": 2304,
133
- "out_hidden_size": 5120,
134
- "patch_size": 16,
135
- "spatial_merge_size": 2,
136
- "temporal_patch_size": 2
137
- },
138
- "vision_end_token_id": 248054,
139
- "vision_start_token_id": 248053
140
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 248044,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 248046,
6
- 248044
7
- ],
8
- "pad_token_id": 248044,
9
- "temperature": 1.0,
10
- "top_k": 20,
11
- "top_p": 0.95
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
27B/base/model-00001-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8401ca8e6e44ae5a6490c03525cdac679d54b45e41e43cf3c98e11a631958ecd
3
- size 3966730552
 
 
 
 
27B/base/model-00002-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecffb87031c4c2f50f229b43e6238495bf79295fdae1bacea51cdfef5fe1684e
3
- size 3043080328
 
 
 
 
27B/base/model-00003-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:de8dc6e96c4438fc5a8cc00563faf9bed85657637125975122d5e7b2a0a04783
3
- size 2542796952
 
 
 
 
27B/base/model-00004-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:96c3830ecf648baaf268717a37bcb34eb5354a1359e65d9b2b363cafbbe6c267
3
- size 3988973152
 
 
 
 
27B/base/model-00005-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:78eb31d00c68d040d9774f823da5ffc3df0918d61417835787b6d9aa21dba2d2
3
- size 2099339864
 
 
 
 
27B/base/model-00006-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fff44f35d3d24a76372e0074d11aebbb8e4e69570ecb712d84df5f44a9fd5359
3
- size 3979553696
 
 
 
 
27B/base/model-00007-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc31bf8400a0a5a13ec9426b11f92eb65e78722b09a4de5ef9fbe8d3deabb957
3
- size 2108759344
 
 
 
 
27B/base/model-00008-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:82f22294aeaf196efbab630433233c4641232eaccf6925e38a336dcf764f9688
3
- size 3979553696
 
 
 
 
27B/base/model-00009-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f703588455e3b86fd1b07759c46692e401b50da4976989e6d96cd56d49afe41a
3
- size 2108759344
 
 
 
 
27B/base/model-00010-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aacf68fc6a0e469c6303687f81c0d79a512b071f68cd8931b98f22dc44bc2f67
3
- size 3979553696
 
 
 
 
27B/base/model-00011-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6467f32acfe5e1ba4b01966370d1b1a7a535a5849ec65ada015e96785bc1dfed
3
- size 2108759344
 
 
 
 
27B/base/model-00012-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13ff1760d6f337a2c8cba47cbc831b21c6ff3eaaa5081233031c361c736f9fa1
3
- size 3979553696
 
 
 
 
27B/base/model-00013-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c47942549ffa0ec109514f98c32984aa4e32770344b29d056bb543836921cdbf
3
- size 2108759344
 
 
 
 
27B/base/model-00014-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:da3c842fbab4c1b513061d52102cc3e6f27222f7c8067643b6b4b8d395113d52
3
- size 3979553696
 
 
 
 
27B/base/model-00015-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:075a517c4cef2f295fa04b266abc8be0b4b4200b9bff8fc24283eb200f73b54c
3
- size 2108759344
 
 
 
 
27B/base/model-00016-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7bcfdc5eb33506f432ffc159029ec8e011842cba58f77222ea41494424cb816
3
- size 3979564040
 
 
 
 
27B/base/model-00017-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3266a898280ba685e632369836d9035fe0777355cc2d506df07c630633fa7115
3
- size 2108759344
 
 
 
 
27B/base/model-00018-of-00018.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a1845882fc0c3c914ff03da77a762b2bebab8828cf66e87fc6ef659d278d5d7
3
- size 3392197344
 
 
 
 
27B/base/model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
27B/base/preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
3
- size 12809320
 
 
 
 
27B/base/tokenizer_config.json DELETED
@@ -1,305 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "248044": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "248045": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "248046": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "248047": {
29
- "content": "<|object_ref_start|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "248048": {
37
- "content": "<|object_ref_end|>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "248049": {
45
- "content": "<|box_start|>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "248050": {
53
- "content": "<|box_end|>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "248051": {
61
- "content": "<|quad_start|>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "248052": {
69
- "content": "<|quad_end|>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "248053": {
77
- "content": "<|vision_start|>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "248054": {
85
- "content": "<|vision_end|>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "248055": {
93
- "content": "<|vision_pad|>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "248056": {
101
- "content": "<|image_pad|>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "248057": {
109
- "content": "<|video_pad|>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "248058": {
117
- "content": "<tool_call>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "248059": {
125
- "content": "</tool_call>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "248060": {
133
- "content": "<|fim_prefix|>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "248061": {
141
- "content": "<|fim_middle|>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "248062": {
149
- "content": "<|fim_suffix|>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "248063": {
157
- "content": "<|fim_pad|>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "248064": {
165
- "content": "<|repo_name|>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "248065": {
173
- "content": "<|file_sep|>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "248066": {
181
- "content": "<tool_response>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "248067": {
189
- "content": "</tool_response>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "248068": {
197
- "content": "<think>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "248069": {
205
- "content": "</think>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "248070": {
213
- "content": "<|audio_start|>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "248071": {
221
- "content": "<|audio_end|>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "248072": {
229
- "content": "<tts_pad>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "248073": {
237
- "content": "<tts_text_bos>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "248074": {
245
- "content": "<tts_text_eod>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "248075": {
253
- "content": "<tts_text_bos_single>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "248076": {
261
- "content": "<|audio_pad|>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- }
268
- },
269
- "additional_special_tokens": [
270
- "<|im_start|>",
271
- "<|im_end|>",
272
- "<|object_ref_start|>",
273
- "<|object_ref_end|>",
274
- "<|box_start|>",
275
- "<|box_end|>",
276
- "<|quad_start|>",
277
- "<|quad_end|>",
278
- "<|vision_start|>",
279
- "<|vision_end|>",
280
- "<|vision_pad|>",
281
- "<|image_pad|>",
282
- "<|video_pad|>"
283
- ],
284
- "bos_token": null,
285
- "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\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 'image' in item or 'image_url' in item or item.type == 'image' %}\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 'video' in item or item.type == 'video' %}\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 {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n {%- endif %}\n {%- if resolved_reasoning_effort == 'xhigh' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n {%- elif resolved_reasoning_effort == 'low' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {%- if reasoning_instructions %}\n {{- reasoning_instructions + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\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>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '') + content + '<|im_end|>\\n' }}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
- "clean_up_tokenization_spaces": false,
287
- "eos_token": "<|im_end|>",
288
- "errors": "replace",
289
- "model_max_length": 262144,
290
- "pad_token": "<|endoftext|>",
291
- "split_special_tokens": false,
292
- "tokenizer_class": "Qwen2Tokenizer",
293
- "unk_token": null,
294
- "add_bos_token": false,
295
- "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+",
296
- "extra_special_tokens": {
297
- "audio_bos_token": "<|audio_start|>",
298
- "audio_eos_token": "<|audio_end|>",
299
- "audio_token": "<|audio_pad|>",
300
- "image_token": "<|image_pad|>",
301
- "video_token": "<|video_pad|>",
302
- "vision_bos_token": "<|vision_start|>",
303
- "vision_eos_token": "<|vision_end|>"
304
- }
305
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/video_preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27B/base/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
9B/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 %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9B/config.json DELETED
@@ -1,103 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "image_token_id": 248056,
6
- "model_type": "qwen3_5",
7
- "text_config": {
8
- "attention_bias": false,
9
- "attention_dropout": 0.0,
10
- "attn_output_gate": true,
11
- "dtype": "bfloat16",
12
- "eos_token_id": 248044,
13
- "full_attention_interval": 4,
14
- "head_dim": 256,
15
- "hidden_act": "silu",
16
- "hidden_size": 4096,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 12288,
19
- "layer_types": [
20
- "linear_attention",
21
- "linear_attention",
22
- "linear_attention",
23
- "full_attention",
24
- "linear_attention",
25
- "linear_attention",
26
- "linear_attention",
27
- "full_attention",
28
- "linear_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "full_attention",
32
- "linear_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "full_attention",
36
- "linear_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "full_attention",
40
- "linear_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "full_attention",
44
- "linear_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "full_attention",
48
- "linear_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "full_attention"
52
- ],
53
- "linear_conv_kernel_dim": 4,
54
- "linear_key_head_dim": 128,
55
- "linear_num_key_heads": 16,
56
- "linear_num_value_heads": 32,
57
- "linear_value_head_dim": 128,
58
- "max_position_embeddings": 262144,
59
- "mlp_only_layers": [],
60
- "model_type": "qwen3_5_text",
61
- "mtp_num_hidden_layers": 1,
62
- "mtp_use_dedicated_embeddings": false,
63
- "num_attention_heads": 16,
64
- "num_hidden_layers": 32,
65
- "num_key_value_heads": 4,
66
- "rms_norm_eps": 1e-06,
67
- "use_cache": true,
68
- "vocab_size": 248320,
69
- "mamba_ssm_dtype": "float32",
70
- "rope_parameters": {
71
- "mrope_interleaved": true,
72
- "mrope_section": [
73
- 11,
74
- 11,
75
- 10
76
- ],
77
- "rope_type": "default",
78
- "rope_theta": 10000000,
79
- "partial_rotary_factor": 0.25
80
- }
81
- },
82
- "tie_word_embeddings": false,
83
- "transformers_version": "4.57.0.dev0",
84
- "video_token_id": 248057,
85
- "vision_config": {
86
- "deepstack_visual_indexes": [],
87
- "depth": 27,
88
- "hidden_act": "gelu_pytorch_tanh",
89
- "hidden_size": 1152,
90
- "in_channels": 3,
91
- "initializer_range": 0.02,
92
- "intermediate_size": 4304,
93
- "model_type": "qwen3_5",
94
- "num_heads": 16,
95
- "num_position_embeddings": 2304,
96
- "out_hidden_size": 4096,
97
- "patch_size": 16,
98
- "spatial_merge_size": 2,
99
- "temporal_patch_size": 2
100
- },
101
- "vision_end_token_id": 248054,
102
- "vision_start_token_id": 248053
103
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9B/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": 248044,
4
- "transformers_version": "5.9.0",
5
- "use_cache": true
6
- }
 
 
 
 
 
 
 
9B/model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58bce582ef74bcde57fd98741921f33a05fdf27f307a71d57f384effc951a21
3
- size 17907663008
 
 
 
 
9B/model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f683d74d5c5a313324f0b38419e80fb4bb2daf214fa432273d7e91dae58984
3
- size 1398643776
 
 
 
 
9B/model.safetensors.index.json DELETED
@@ -1,782 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 19306208736
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00001-of-00002.safetensors",
7
- "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
10
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
11
- "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
12
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
13
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
14
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
15
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
16
- "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
17
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
18
- "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
23
- "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
24
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
25
- "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
26
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
27
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
28
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
29
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
30
- "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
31
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
- "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
38
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
39
- "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
40
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
41
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
42
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
43
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
44
- "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
45
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
- "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
- "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
- "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
54
- "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
55
- "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
56
- "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
57
- "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
59
- "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
- "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
63
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
64
- "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
65
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
66
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
67
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
68
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
69
- "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
70
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
- "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
- "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
77
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
78
- "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
79
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
80
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
81
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
82
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
83
- "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
84
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
89
- "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
91
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
92
- "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
93
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
94
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
95
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
96
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
97
- "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
98
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
99
- "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
- "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
- "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
- "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
109
- "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
112
- "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
115
- "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
116
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
117
- "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
118
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
119
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
120
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
121
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
122
- "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
123
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
126
- "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
- "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
130
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
131
- "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
132
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
133
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
134
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
135
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
136
- "model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
137
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
138
- "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
139
- "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
140
- "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
142
- "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
143
- "model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
144
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
145
- "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
146
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
147
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
148
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
149
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
150
- "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
151
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
152
- "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
- "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
- "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
- "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
157
- "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
161
- "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
162
- "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
163
- "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
165
- "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
- "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
167
- "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
168
- "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
169
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
170
- "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
171
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
172
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
173
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
174
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
175
- "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
176
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
179
- "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
180
- "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
181
- "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
- "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors",
183
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
184
- "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
185
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
186
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
187
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
188
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
189
- "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
190
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
192
- "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
195
- "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
- "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors",
197
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
198
- "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
199
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
200
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
201
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
202
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
203
- "model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
204
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
206
- "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
208
- "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
209
- "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
210
- "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors",
211
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
212
- "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
213
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
214
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
215
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
216
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
217
- "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
218
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
220
- "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
222
- "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
223
- "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
- "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
- "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
229
- "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
232
- "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
- "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
235
- "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors",
236
- "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
237
- "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
238
- "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
239
- "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
240
- "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
241
- "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
242
- "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
243
- "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
247
- "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
248
- "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
249
- "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors",
250
- "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
251
- "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
252
- "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
253
- "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
254
- "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
255
- "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
256
- "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
257
- "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
261
- "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
262
- "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
- "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors",
264
- "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
265
- "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
266
- "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
267
- "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
268
- "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
269
- "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
270
- "model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
271
- "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
273
- "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
274
- "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
276
- "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
277
- "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
278
- "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
279
- "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
280
- "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
281
- "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
282
- "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
283
- "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
284
- "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
285
- "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
- "model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors",
289
- "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
290
- "model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
291
- "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
292
- "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
293
- "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
294
- "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
295
- "model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
296
- "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
297
- "model.language_model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
298
- "model.language_model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
299
- "model.language_model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
300
- "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
301
- "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
302
- "model.language_model.layers.29.linear_attn.A_log": "model-00001-of-00002.safetensors",
303
- "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
304
- "model.language_model.layers.29.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
305
- "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
306
- "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
307
- "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
308
- "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
309
- "model.language_model.layers.29.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
310
- "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
311
- "model.language_model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
312
- "model.language_model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
313
- "model.language_model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
314
- "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
315
- "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
316
- "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
317
- "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
318
- "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
319
- "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
320
- "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
321
- "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
322
- "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
323
- "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
324
- "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
325
- "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
326
- "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
327
- "model.language_model.layers.30.linear_attn.A_log": "model-00001-of-00002.safetensors",
328
- "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
329
- "model.language_model.layers.30.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
330
- "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
331
- "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
332
- "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
333
- "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
334
- "model.language_model.layers.30.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
335
- "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
336
- "model.language_model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
337
- "model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
338
- "model.language_model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
339
- "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
340
- "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
341
- "model.language_model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
342
- "model.language_model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
343
- "model.language_model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
344
- "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
345
- "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
346
- "model.language_model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
347
- "model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
348
- "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
349
- "model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
350
- "model.language_model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
351
- "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
352
- "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
353
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
354
- "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
355
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
356
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
357
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
358
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
359
- "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
360
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
361
- "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
- "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
- "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
- "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
- "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
366
- "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
367
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
368
- "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
369
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
370
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
371
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
372
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
373
- "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
374
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
375
- "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
376
- "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
377
- "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
378
- "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
379
- "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
380
- "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
381
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
382
- "model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
383
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
384
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
385
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
386
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
387
- "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
388
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
389
- "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
391
- "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
392
- "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
393
- "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
- "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
- "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
- "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
- "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
- "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
- "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
- "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
- "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
- "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
- "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
- "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
- "model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
406
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
407
- "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
408
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
409
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
410
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
411
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
412
- "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
413
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
414
- "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
415
- "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
416
- "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
417
- "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
418
- "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
419
- "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
420
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
421
- "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
422
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
423
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
424
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
425
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
426
- "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
427
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
428
- "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
430
- "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
- "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
- "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
433
- "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
434
- "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
435
- "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
436
- "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
437
- "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
438
- "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
439
- "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
440
- "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
441
- "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
442
- "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
443
- "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
444
- "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
445
- "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
446
- "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
447
- "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
448
- "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
449
- "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
450
- "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
451
- "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
452
- "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
453
- "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
454
- "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
455
- "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
456
- "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
457
- "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
458
- "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
459
- "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
460
- "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
461
- "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
462
- "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
463
- "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
464
- "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
465
- "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
466
- "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
467
- "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
468
- "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
469
- "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
470
- "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
471
- "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
472
- "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
473
- "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
474
- "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
475
- "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
476
- "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
477
- "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
478
- "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
479
- "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
480
- "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
481
- "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
482
- "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
483
- "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
484
- "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
485
- "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
486
- "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
487
- "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
488
- "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
489
- "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
490
- "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
491
- "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
492
- "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
493
- "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
494
- "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
495
- "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
496
- "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
497
- "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
498
- "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
499
- "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
500
- "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
501
- "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
502
- "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
503
- "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
504
- "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
505
- "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
506
- "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
507
- "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
508
- "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
509
- "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
510
- "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
511
- "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
512
- "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
513
- "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
514
- "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
515
- "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
516
- "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
517
- "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
518
- "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
519
- "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
520
- "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
521
- "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
522
- "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
523
- "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
524
- "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
525
- "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
526
- "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
527
- "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
528
- "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
529
- "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
530
- "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
531
- "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
532
- "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
533
- "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
534
- "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
535
- "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
536
- "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
537
- "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
538
- "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
539
- "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
540
- "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
541
- "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
542
- "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
543
- "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
544
- "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
545
- "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
546
- "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
547
- "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
548
- "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
549
- "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
550
- "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
551
- "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
552
- "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
553
- "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
554
- "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
555
- "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
556
- "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
557
- "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
558
- "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
559
- "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
560
- "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
561
- "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
562
- "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
563
- "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
564
- "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
565
- "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
566
- "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
567
- "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
568
- "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
569
- "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
570
- "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
571
- "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
572
- "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
573
- "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
574
- "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
575
- "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
576
- "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
577
- "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
578
- "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
579
- "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
580
- "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
581
- "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
582
- "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
583
- "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
584
- "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
585
- "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
586
- "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
587
- "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
588
- "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
589
- "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
590
- "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
591
- "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
592
- "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
593
- "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
594
- "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
595
- "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
596
- "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
597
- "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
598
- "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
599
- "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
600
- "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
601
- "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
602
- "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
603
- "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
604
- "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
605
- "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
606
- "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
607
- "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
608
- "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
609
- "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
610
- "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
611
- "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
612
- "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
613
- "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
614
- "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
615
- "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
616
- "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
617
- "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
618
- "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
619
- "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
620
- "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
621
- "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
622
- "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
623
- "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
624
- "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
625
- "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
626
- "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
627
- "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
628
- "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
629
- "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
630
- "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
631
- "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
632
- "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
633
- "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
634
- "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
635
- "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
636
- "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
637
- "model.visual.blocks.24.attn.proj.bias": "model-00002-of-00002.safetensors",
638
- "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
639
- "model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00002.safetensors",
640
- "model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
641
- "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
642
- "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
643
- "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
644
- "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
645
- "model.visual.blocks.24.norm1.bias": "model-00002-of-00002.safetensors",
646
- "model.visual.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
647
- "model.visual.blocks.24.norm2.bias": "model-00002-of-00002.safetensors",
648
- "model.visual.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
649
- "model.visual.blocks.25.attn.proj.bias": "model-00002-of-00002.safetensors",
650
- "model.visual.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
651
- "model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00002.safetensors",
652
- "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
653
- "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
654
- "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
655
- "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
656
- "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
657
- "model.visual.blocks.25.norm1.bias": "model-00002-of-00002.safetensors",
658
- "model.visual.blocks.25.norm1.weight": "model-00002-of-00002.safetensors",
659
- "model.visual.blocks.25.norm2.bias": "model-00002-of-00002.safetensors",
660
- "model.visual.blocks.25.norm2.weight": "model-00002-of-00002.safetensors",
661
- "model.visual.blocks.26.attn.proj.bias": "model-00002-of-00002.safetensors",
662
- "model.visual.blocks.26.attn.proj.weight": "model-00002-of-00002.safetensors",
663
- "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00002.safetensors",
664
- "model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00002.safetensors",
665
- "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
666
- "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
667
- "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
668
- "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
669
- "model.visual.blocks.26.norm1.bias": "model-00002-of-00002.safetensors",
670
- "model.visual.blocks.26.norm1.weight": "model-00002-of-00002.safetensors",
671
- "model.visual.blocks.26.norm2.bias": "model-00002-of-00002.safetensors",
672
- "model.visual.blocks.26.norm2.weight": "model-00002-of-00002.safetensors",
673
- "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
674
- "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
675
- "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
676
- "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
677
- "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
678
- "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
679
- "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
680
- "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
681
- "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
682
- "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
683
- "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
684
- "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
685
- "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
686
- "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
687
- "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
688
- "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
689
- "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
690
- "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
691
- "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
692
- "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
693
- "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
694
- "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
695
- "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
696
- "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
697
- "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
698
- "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
699
- "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
700
- "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
701
- "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
702
- "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
703
- "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
704
- "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
705
- "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
706
- "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
707
- "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
708
- "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
709
- "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
710
- "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
711
- "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
712
- "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
713
- "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
714
- "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
715
- "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
716
- "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
717
- "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
718
- "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
719
- "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
720
- "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
721
- "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
722
- "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
723
- "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
724
- "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
725
- "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
726
- "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
727
- "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
728
- "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
729
- "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
730
- "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
731
- "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
732
- "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
733
- "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
734
- "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
735
- "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
736
- "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
737
- "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
738
- "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
739
- "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
740
- "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
741
- "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
742
- "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
743
- "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
744
- "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
745
- "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
746
- "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
747
- "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
748
- "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
749
- "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
750
- "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
751
- "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
752
- "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
753
- "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
754
- "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
755
- "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
756
- "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
757
- "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
758
- "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
759
- "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
760
- "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
761
- "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
762
- "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
763
- "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
764
- "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
765
- "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors",
766
- "mtp.fc.weight": "model-00002-of-00002.safetensors",
767
- "mtp.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
768
- "mtp.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
769
- "mtp.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
770
- "mtp.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
771
- "mtp.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
772
- "mtp.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
773
- "mtp.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
774
- "mtp.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
775
- "mtp.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
776
- "mtp.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
777
- "mtp.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
778
- "mtp.norm.weight": "model-00002-of-00002.safetensors",
779
- "mtp.pre_fc_norm_embedding.weight": "model-00002-of-00002.safetensors",
780
- "mtp.pre_fc_norm_hidden.weight": "model-00002-of-00002.safetensors"
781
- }
782
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9B/preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9B/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
- size 19989325
 
 
 
 
9B/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": "<|im_end|>",
10
- "errors": "replace",
11
- "image_token": "<|image_pad|>",
12
- "is_local": true,
13
- "local_files_only": true,
14
- "model_max_length": 262144,
15
- "model_specific_special_tokens": {
16
- "audio_bos_token": "<|audio_start|>",
17
- "audio_eos_token": "<|audio_end|>",
18
- "audio_token": "<|audio_pad|>",
19
- "image_token": "<|image_pad|>",
20
- "video_token": "<|video_pad|>",
21
- "vision_bos_token": "<|vision_start|>",
22
- "vision_eos_token": "<|vision_end|>"
23
- },
24
- "pad_token": "<|endoftext|>",
25
- "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+",
26
- "split_special_tokens": false,
27
- "tokenizer_class": "Qwen2Tokenizer",
28
- "unk_token": null,
29
- "video_token": "<|video_pad|>",
30
- "vision_bos_token": "<|vision_start|>",
31
- "vision_eos_token": "<|vision_end|>"
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9B/video_preprocessor_config.json DELETED
@@ -1,21 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
NOTICE CHANGED
@@ -8,10 +8,7 @@ Their license files are retained in licenses/Qwen3.8-27B/LICENSE and
8
  licenses/Qwen3.5-9B/LICENSE.
9
 
10
  Postgres Professional modified the model parameters through continued
11
- pretraining, supervised fine-tuning and reinforcement learning. Slonik-27B
12
- retains its reinforcement-learning adapter separately from its adapted base.
13
- Slonik-9B contains the evaluated full-weight export with that adapter merged.
14
- Configuration metadata was adjusted for portable loading.
15
 
16
  The Apache License, Version 2.0 applies to the released model weights,
17
  configuration files and accompanying loading examples. The report and
 
8
  licenses/Qwen3.5-9B/LICENSE.
9
 
10
  Postgres Professional modified the model parameters through continued
11
+ pretraining, supervised fine-tuning and reinforcement learning.
 
 
 
12
 
13
  The Apache License, Version 2.0 applies to the released model weights,
14
  configuration files and accompanying loading examples. The report and
README.md CHANGED
@@ -1,10 +1,6 @@
1
  ---
2
  pipeline_tag: text-generation
3
- library_name: transformers
4
  license: apache-2.0
5
- base_model:
6
- - Qwen/Qwen3.8-27B
7
- - Qwen/Qwen3.5-9B
8
  inference: false
9
  tags:
10
  - slonik
@@ -12,8 +8,7 @@ tags:
12
  - postgresql
13
  - software-engineering
14
  - reinforcement-learning
15
- - peft
16
- - safetensors
17
  ---
18
 
19
  # Slonik
@@ -24,8 +19,8 @@ November 2026
24
 
25
  [Technical report (PDF)](Slonik.pdf)
26
 
27
- [Slonik-27B weights](https://huggingface.co/dglhf/Slonik/tree/main/27B)
28
- [Slonik-9B weights](https://huggingface.co/dglhf/Slonik/tree/main/9B)
29
  [Apache 2.0](LICENSE)
30
 
31
  Database engines are critical infrastructure, yet their development remains an underexplored setting for coding agents. A PostgreSQL patch must connect systems code with behavior exposed through SQL; successful compilation alone does not establish correctness. Existing database environments often study [tuning](https://vldb.org/cidrdb/2023/database-gyms.html) or [SQL debugging](https://arxiv.org/abs/2506.18951), while engine-development tasks require changes to the database implementation itself.
@@ -41,92 +36,18 @@ PostgreSQL supplies source-level repair tasks, built-in C function tasks, extens
41
  | Slonik-27B | [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) | DAPO update 116 |
42
  | Slonik-9B | [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) | DAPO update 177 |
43
 
44
- The starting checkpoints belong to different backbone families, so the comparison does not isolate parameter count. Headline Slonik-27B scores use a LoRA adapter over the fully adapted CPT + SFT checkpoint. Load the released `27B/base` checkpoint together with `27B/adapter`. Slonik-9B uses the evaluated full-weight export in `9B`, with its RL adapter already merged.
45
 
46
  The Slonik-9B run later reached update 397, which has no complete five-suite evaluation in this report. Its SWE-bench score at update 177 is provisional; one evaluation round completed 55 of 58 tasks.
47
 
48
  ## Download and Run
49
 
50
- The repository contains both models under one card. Choose the corresponding folder when downloading.
51
-
52
- | Model | Files | Loading |
53
  | --- | --- | --- |
54
- | Slonik-27B | `27B/base/`, `27B/adapter/` | Adapted CPT + SFT base with the separate RL adapter |
55
- | Slonik-9B | `9B/` | Complete evaluated checkpoint; no additional adapter |
56
-
57
- The files use Safetensors. The original `qwen3_5` architecture metadata is retained. Evaluation concerns text/code workflows; the retained vision components have not been evaluated here. File hashes are listed in [checksums.sha256](checksums.sha256).
58
-
59
- ### Transformers
60
-
61
- The loading check uses Transformers 5.9.0, PEFT 0.19.1, Accelerate 1.14.0, PyTorch 2.11.0. Use a PyTorch build suitable for your hardware.
62
-
63
- ```bash
64
- pip install "transformers==5.9.0" "peft==0.19.1" "accelerate==1.14.0" huggingface_hub
65
- ```
66
-
67
- ```python
68
- from pathlib import Path
69
-
70
- import torch
71
- from huggingface_hub import snapshot_download
72
- from peft import PeftModel
73
- from transformers import AutoModelForImageTextToText, AutoTokenizer
74
-
75
- size = "9B" # "27B" selects the base plus adapter.
76
- folder = Path(snapshot_download(
77
- "dglhf/Slonik",
78
- allow_patterns=[f"{size}/*", "LICENSE", "NOTICE", "licenses/*"],
79
- )) / size
80
- base = folder / "base" if size == "27B" else folder
81
-
82
- tokenizer = AutoTokenizer.from_pretrained(base)
83
- model = AutoModelForImageTextToText.from_pretrained(
84
- base, dtype=torch.bfloat16, device_map="auto",
85
- )
86
- if size == "27B":
87
- model = PeftModel.from_pretrained(
88
- model, folder / "adapter", autocast_adapter_dtype=False,
89
- )
90
- model.eval()
91
-
92
- messages = [{"role": "user", "content": "Explain how PostgreSQL MVCC visibility works."}]
93
- prompt = tokenizer.apply_chat_template(
94
- messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,
95
- )
96
- inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
97
- with torch.inference_mode():
98
- outputs = model.generate(
99
- **inputs, max_new_tokens=512, do_sample=True,
100
- temperature=1.0, top_p=0.95, top_k=20,
101
- )
102
- print(tokenizer.decode(outputs[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))
103
- ```
104
-
105
- The 27B adapter metadata contains no server-specific base path. Load the base explicitly as shown above. Attaching this adapter directly to the original Qwen checkpoint does not reproduce Slonik-27B.
106
-
107
- ### vLLM
108
-
109
- Download the selected folder with `snapshot_download` above, then substitute its local path in these commands. The recorded serving configuration uses the `qwen3_coder` tool parser, text-only serving, thinking disabled. Tensor parallelism can be adjusted to the available GPUs.
110
-
111
- ```bash
112
- vllm serve /path/to/Slonik/9B \
113
- --served-model-name Slonik-9B \
114
- --language-model-only --max-model-len 32768 \
115
- --enable-auto-tool-choice --tool-call-parser qwen3_coder \
116
- --default-chat-template-kwargs '{"enable_thinking": false}'
117
- ```
118
-
119
- ```bash
120
- vllm serve /path/to/Slonik/27B/base \
121
- --served-model-name Slonik-27B-base \
122
- --enable-lora --max-lora-rank 16 \
123
- --lora-modules Slonik-27B=/path/to/Slonik/27B/adapter \
124
- --language-model-only --max-model-len 32768 \
125
- --enable-auto-tool-choice --tool-call-parser qwen3_coder \
126
- --default-chat-template-kwargs '{"enable_thinking": false}'
127
- ```
128
-
129
- Send inference requests with `model="Slonik-9B"` or `model="Slonik-27B"`. Tool execution, the conversation loop, task environments belong to the calling agent harness.
130
 
131
  ## Uses
132
 
@@ -166,7 +87,7 @@ The evaluation uses a 60-turn limit with a 28,000-token prompt budget. Terminal-
166
 
167
  ![Slonik benchmark comparison](assets/benchmarks.svg)
168
 
169
- **Benchmark results, pass@1 (%).**
170
 
171
  | Model | PG17 | PG18 | Apache AGE | SWE-bench Verified subset | Terminal-Bench 2.0 subset |
172
  | --- | ---: | ---: | ---: | ---: | ---: |
 
1
  ---
2
  pipeline_tag: text-generation
 
3
  license: apache-2.0
 
 
 
4
  inference: false
5
  tags:
6
  - slonik
 
8
  - postgresql
9
  - software-engineering
10
  - reinforcement-learning
11
+ - model-card-only
 
12
  ---
13
 
14
  # Slonik
 
19
 
20
  [Technical report (PDF)](Slonik.pdf)
21
 
22
+ [Slonik-27B weights](https://huggingface.co/dglhf/Slonik-27B)
23
+ [Slonik-9B weights](https://huggingface.co/dglhf/Slonik-9B)
24
  [Apache 2.0](LICENSE)
25
 
26
  Database engines are critical infrastructure, yet their development remains an underexplored setting for coding agents. A PostgreSQL patch must connect systems code with behavior exposed through SQL; successful compilation alone does not establish correctness. Existing database environments often study [tuning](https://vldb.org/cidrdb/2023/database-gyms.html) or [SQL debugging](https://arxiv.org/abs/2506.18951), while engine-development tasks require changes to the database implementation itself.
 
36
  | Slonik-27B | [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) | DAPO update 116 |
37
  | Slonik-9B | [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) | DAPO update 177 |
38
 
39
+ The starting checkpoints belong to different backbone families, so the comparison does not isolate parameter count. Both models are available as complete BF16 checkpoints in their respective repositories.
40
 
41
  The Slonik-9B run later reached update 397, which has no complete five-suite evaluation in this report. Its SWE-bench score at update 177 is provisional; one evaluation round completed 55 of 58 tasks.
42
 
43
  ## Download and Run
44
 
45
+ | Model | Repository | Instructions |
 
 
46
  | --- | --- | --- |
47
+ | Slonik-27B | [dglhf/Slonik-27B](https://huggingface.co/dglhf/Slonik-27B) | [Transformers and vLLM](https://huggingface.co/dglhf/Slonik-27B#usage) |
48
+ | Slonik-9B | [dglhf/Slonik-9B](https://huggingface.co/dglhf/Slonik-9B) | [Transformers and vLLM](https://huggingface.co/dglhf/Slonik-9B#usage) |
49
+
50
+ Each repository contains the model weights, tokenizer, chat template, configuration files. This page contains the shared research overview and technical report.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
  ## Uses
53
 
 
87
 
88
  ![Slonik benchmark comparison](assets/benchmarks.svg)
89
 
90
+ **Benchmark results from the technical report, pass@1 (%).**
91
 
92
  | Model | PG17 | PG18 | Apache AGE | SWE-bench Verified subset | Terminal-Bench 2.0 subset |
93
  | --- | ---: | ---: | ---: | ---: | ---: |
checksums.sha256 DELETED
@@ -1,40 +0,0 @@
1
- c0a9f00e1e54796b8c0260999db68969b1a2fcf1742a309b6d2be6f0a3288a2d 27B/adapter/adapter_config.json
2
- 41b3763b530ac5dd1f4d2d19b1b1765f7cb611b826bab8b6cc456d95a5b1077f 27B/adapter/adapter_model.safetensors
3
- c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041 27B/base/chat_template.jinja
4
- 7718cd6bf3d6521d5550966d4ab8484fc81a01347d74b7e52163070f35ca7f35 27B/base/config.json
5
- e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e 27B/base/generation_config.json
6
- a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d 27B/base/merges.txt
7
- 8401ca8e6e44ae5a6490c03525cdac679d54b45e41e43cf3c98e11a631958ecd 27B/base/model-00001-of-00018.safetensors
8
- ecffb87031c4c2f50f229b43e6238495bf79295fdae1bacea51cdfef5fe1684e 27B/base/model-00002-of-00018.safetensors
9
- de8dc6e96c4438fc5a8cc00563faf9bed85657637125975122d5e7b2a0a04783 27B/base/model-00003-of-00018.safetensors
10
- 96c3830ecf648baaf268717a37bcb34eb5354a1359e65d9b2b363cafbbe6c267 27B/base/model-00004-of-00018.safetensors
11
- 78eb31d00c68d040d9774f823da5ffc3df0918d61417835787b6d9aa21dba2d2 27B/base/model-00005-of-00018.safetensors
12
- fff44f35d3d24a76372e0074d11aebbb8e4e69570ecb712d84df5f44a9fd5359 27B/base/model-00006-of-00018.safetensors
13
- dc31bf8400a0a5a13ec9426b11f92eb65e78722b09a4de5ef9fbe8d3deabb957 27B/base/model-00007-of-00018.safetensors
14
- 82f22294aeaf196efbab630433233c4641232eaccf6925e38a336dcf764f9688 27B/base/model-00008-of-00018.safetensors
15
- f703588455e3b86fd1b07759c46692e401b50da4976989e6d96cd56d49afe41a 27B/base/model-00009-of-00018.safetensors
16
- aacf68fc6a0e469c6303687f81c0d79a512b071f68cd8931b98f22dc44bc2f67 27B/base/model-00010-of-00018.safetensors
17
- 6467f32acfe5e1ba4b01966370d1b1a7a535a5849ec65ada015e96785bc1dfed 27B/base/model-00011-of-00018.safetensors
18
- 13ff1760d6f337a2c8cba47cbc831b21c6ff3eaaa5081233031c361c736f9fa1 27B/base/model-00012-of-00018.safetensors
19
- c47942549ffa0ec109514f98c32984aa4e32770344b29d056bb543836921cdbf 27B/base/model-00013-of-00018.safetensors
20
- da3c842fbab4c1b513061d52102cc3e6f27222f7c8067643b6b4b8d395113d52 27B/base/model-00014-of-00018.safetensors
21
- 075a517c4cef2f295fa04b266abc8be0b4b4200b9bff8fc24283eb200f73b54c 27B/base/model-00015-of-00018.safetensors
22
- f7bcfdc5eb33506f432ffc159029ec8e011842cba58f77222ea41494424cb816 27B/base/model-00016-of-00018.safetensors
23
- 3266a898280ba685e632369836d9035fe0777355cc2d506df07c630633fa7115 27B/base/model-00017-of-00018.safetensors
24
- 3a1845882fc0c3c914ff03da77a762b2bebab8828cf66e87fc6ef659d278d5d7 27B/base/model-00018-of-00018.safetensors
25
- c4a75159c861f779f00231b288228db38b133cbee67546da6ee8c709664c9aa8 27B/base/model.safetensors.index.json
26
- 27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516 27B/base/preprocessor_config.json
27
- 0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3 27B/base/tokenizer.json
28
- 60e96a382893c9efeb7116fb83e2c532cb149d00bfd859713640c0a8ae282019 27B/base/tokenizer_config.json
29
- 7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13 27B/base/video_preprocessor_config.json
30
- ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003 27B/base/vocab.json
31
- a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715 9B/chat_template.jinja
32
- cb1a0d3d7f169532311b6f5d5ee6a649c49667248878fdfe22f163dc16797070 9B/config.json
33
- 5b7ccdaa98f0c7ddfc66ae6c6e2dcf384ffbc670665ccfbf966979c8ebf8308d 9B/generation_config.json
34
- c58bce582ef74bcde57fd98741921f33a05fdf27f307a71d57f384effc951a21 9B/model-00001-of-00002.safetensors
35
- 64f683d74d5c5a313324f0b38419e80fb4bb2daf214fa432273d7e91dae58984 9B/model-00002-of-00002.safetensors
36
- 607b21203142410ef2475feda72dae558d05997069beea49181ad2e5c55aa79c 9B/model.safetensors.index.json
37
- 27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516 9B/preprocessor_config.json
38
- 06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 9B/tokenizer.json
39
- bee8eba30f0eb4af73c0fe2cd06d0f89b657d7819941c438157ec42f7c80ea87 9B/tokenizer_config.json
40
- 7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13 9B/video_preprocessor_config.json