Hugging Face's logo

usermma
/
Qwable-v1-mlx-6Bit

Text Generation
Transformers
Safetensors
MLX
English
qwen3_5_moe
image-text-to-text
qwen
qwen3
qwen3.6
Mixture of Experts
distillation
chain-of-thought
agentic
claude-fable-5
claude-opus-4.7
tool-use
chained-distill
mlx-my-repo
conversational
6-bit
Model card Files
xet
 Community
usermma commited on
Commit
f8f14d0
·
verified ·
1 Parent(s): 52ad94a

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +50 -0
  3. chat_template.jinja +158 -0
  4. config.json +759 -0
  5. model-00001-of-00006.safetensors +3 -0
  6. model-00002-of-00006.safetensors +3 -0
  7. model-00003-of-00006.safetensors +3 -0
  8. model-00004-of-00006.safetensors +3 -0
  9. model-00005-of-00006.safetensors +3 -0
  10. model-00006-of-00006.safetensors +3 -0
  11. model.safetensors.index.json +0 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +34 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: agpl-3.0
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ tags:
7
+ - qwen
8
+ - qwen3
9
+ - qwen3.6
10
+ - moe
11
+ - distillation
12
+ - chain-of-thought
13
+ - agentic
14
+ - claude-fable-5
15
+ - claude-opus-4.7
16
+ - tool-use
17
+ - chained-distill
18
+ - mlx
19
+ - mlx-my-repo
20
+ pipeline_tag: text-generation
21
+ base_model: lordx64/Qwable-v1
22
+ datasets:
23
+ - lordx64/agentic-distill-fable-5-sft
24
+ ---
25
+
26
+ # usermma/Qwable-v1-mlx-6Bit
27
+
28
+ The Model [usermma/Qwable-v1-mlx-6Bit](https://huggingface.co/usermma/Qwable-v1-mlx-6Bit) was converted to MLX format from [lordx64/Qwable-v1](https://huggingface.co/lordx64/Qwable-v1) using mlx-lm version **0.31.2**.
29
+
30
+ ## Use with mlx
31
+
32
+ ```bash
33
+ pip install mlx-lm
34
+ ```
35
+
36
+ ```python
37
+ from mlx_lm import load, generate
38
+
39
+ model, tokenizer = load("usermma/Qwable-v1-mlx-6Bit")
40
+
41
+ prompt="hello"
42
+
43
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
44
+ messages = [{"role": "user", "content": prompt}]
45
+ prompt = tokenizer.apply_chat_template(
46
+ messages, tokenize=False, add_generation_prompt=True
47
+ )
48
+
49
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
50
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 num_sys = 0 %}
46
+ {%- set merged_system = '' %}
47
+ {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
48
+ {%- set first = render_content(messages[0].content, false, true)|trim %}
49
+ {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
50
+ {%- set second = render_content(messages[1].content, false, true)|trim %}
51
+ {%- set merged_system = first + '\n' + second %}
52
+ {%- set num_sys = 2 %}
53
+ {%- else %}
54
+ {%- set merged_system = first %}
55
+ {%- set num_sys = 1 %}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- if tools and tools is iterable and tools is not mapping %}
59
+ {{- '<|im_start|>system\n' }}
60
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
61
+ {%- for tool in tools %}
62
+ {{- "\n" }}
63
+ {{- tool | tojson }}
64
+ {%- endfor %}
65
+ {{- "\n</tools>" }}
66
+ {{- '\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>' }}
67
+ {%- if merged_system %}
68
+ {{- '\n\n' + merged_system }}
69
+ {%- endif %}
70
+ {{- '<|im_end|>\n' }}
71
+ {%- else %}
72
+ {%- if merged_system %}
73
+ {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
77
+ {%- for message in messages[::-1] %}
78
+ {%- set index = (messages|length - 1) - loop.index0 %}
79
+ {%- if ns.multi_step_tool and message.role == "user" %}
80
+ {%- set content = render_content(message.content, false)|trim %}
81
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
82
+ {%- set ns.multi_step_tool = false %}
83
+ {%- set ns.last_query_index = index %}
84
+ {%- endif %}
85
+ {%- endif %}
86
+ {%- endfor %}
87
+ {%- for message in messages %}
88
+ {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
89
+ {%- set content = render_content(message.content, true)|trim %}
90
+ {%- if message.role == "user" %}
91
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
92
+ {%- elif message.role == "assistant" %}
93
+ {%- set reasoning_content = '' %}
94
+ {%- if message.reasoning_content is string %}
95
+ {%- set reasoning_content = message.reasoning_content %}
96
+ {%- else %}
97
+ {%- if '</think>' in content %}
98
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
99
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
100
+ {%- endif %}
101
+ {%- endif %}
102
+ {%- set reasoning_content = reasoning_content|trim %}
103
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
104
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
105
+ {%- else %}
106
+ {{- '<|im_start|>' + message.role + '\n' + content }}
107
+ {%- endif %}
108
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
109
+ {%- for tool_call in message.tool_calls %}
110
+ {%- if tool_call.function is defined %}
111
+ {%- set tool_call = tool_call.function %}
112
+ {%- endif %}
113
+ {%- if loop.first %}
114
+ {%- if content|trim %}
115
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
116
+ {%- else %}
117
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- else %}
120
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
121
+ {%- endif %}
122
+ {%- if tool_call.arguments is mapping %}
123
+ {%- for args_name in tool_call.arguments %}
124
+ {%- set args_value = tool_call.arguments[args_name] %}
125
+ {{- '<parameter=' + args_name + '>\n' }}
126
+ {%- 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 %}
127
+ {{- args_value }}
128
+ {{- '\n</parameter>\n' }}
129
+ {%- endfor %}
130
+ {%- endif %}
131
+ {{- '</function>\n</tool_call>' }}
132
+ {%- endfor %}
133
+ {%- endif %}
134
+ {{- '<|im_end|>\n' }}
135
+ {%- elif message.role == "tool" %}
136
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
137
+ {{- '<|im_start|>user' }}
138
+ {%- endif %}
139
+ {{- '\n<tool_response>\n' }}
140
+ {{- content }}
141
+ {{- '\n</tool_response>' }}
142
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
143
+ {{- '<|im_end|>\n' }}
144
+ {%- elif loop.last %}
145
+ {{- '<|im_end|>\n' }}
146
+ {%- endif %}
147
+ {%- endif %}
148
+ {%- endif %}
149
+ {%- endfor %}
150
+ {%- if add_generation_prompt %}
151
+ {{- '<|im_start|>assistant\n' }}
152
+ {%- if enable_thinking is defined and enable_thinking is false %}
153
+ {{- '<think>\n\n</think>\n\n' }}
154
+ {%- else %}
155
+ {{- '<think>\n' }}
156
+ {%- endif %}
157
+ {%- endif %}
158
+ {#- Unsloth fixes - developer role, tool calling #}
config.json ADDED
@@ -0,0 +1,759 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled",
9
+ "model_type": "qwen3_5_moe",
10
+ "pad_token_id": 248055,
11
+ "quantization": {
12
+ "group_size": 64,
13
+ "bits": 6,
14
+ "mode": "affine",
15
+ "language_model.model.layers.0.mlp.gate": {
16
+ "group_size": 64,
17
+ "bits": 8
18
+ },
19
+ "language_model.model.layers.0.mlp.shared_expert_gate": {
20
+ "group_size": 64,
21
+ "bits": 8
22
+ },
23
+ "language_model.model.layers.1.mlp.gate": {
24
+ "group_size": 64,
25
+ "bits": 8
26
+ },
27
+ "language_model.model.layers.1.mlp.shared_expert_gate": {
28
+ "group_size": 64,
29
+ "bits": 8
30
+ },
31
+ "language_model.model.layers.2.mlp.gate": {
32
+ "group_size": 64,
33
+ "bits": 8
34
+ },
35
+ "language_model.model.layers.2.mlp.shared_expert_gate": {
36
+ "group_size": 64,
37
+ "bits": 8
38
+ },
39
+ "language_model.model.layers.3.mlp.gate": {
40
+ "group_size": 64,
41
+ "bits": 8
42
+ },
43
+ "language_model.model.layers.3.mlp.shared_expert_gate": {
44
+ "group_size": 64,
45
+ "bits": 8
46
+ },
47
+ "language_model.model.layers.4.mlp.gate": {
48
+ "group_size": 64,
49
+ "bits": 8
50
+ },
51
+ "language_model.model.layers.4.mlp.shared_expert_gate": {
52
+ "group_size": 64,
53
+ "bits": 8
54
+ },
55
+ "language_model.model.layers.5.mlp.gate": {
56
+ "group_size": 64,
57
+ "bits": 8
58
+ },
59
+ "language_model.model.layers.5.mlp.shared_expert_gate": {
60
+ "group_size": 64,
61
+ "bits": 8
62
+ },
63
+ "language_model.model.layers.6.mlp.gate": {
64
+ "group_size": 64,
65
+ "bits": 8
66
+ },
67
+ "language_model.model.layers.6.mlp.shared_expert_gate": {
68
+ "group_size": 64,
69
+ "bits": 8
70
+ },
71
+ "language_model.model.layers.7.mlp.gate": {
72
+ "group_size": 64,
73
+ "bits": 8
74
+ },
75
+ "language_model.model.layers.7.mlp.shared_expert_gate": {
76
+ "group_size": 64,
77
+ "bits": 8
78
+ },
79
+ "language_model.model.layers.8.mlp.gate": {
80
+ "group_size": 64,
81
+ "bits": 8
82
+ },
83
+ "language_model.model.layers.8.mlp.shared_expert_gate": {
84
+ "group_size": 64,
85
+ "bits": 8
86
+ },
87
+ "language_model.model.layers.9.mlp.gate": {
88
+ "group_size": 64,
89
+ "bits": 8
90
+ },
91
+ "language_model.model.layers.9.mlp.shared_expert_gate": {
92
+ "group_size": 64,
93
+ "bits": 8
94
+ },
95
+ "language_model.model.layers.10.mlp.gate": {
96
+ "group_size": 64,
97
+ "bits": 8
98
+ },
99
+ "language_model.model.layers.10.mlp.shared_expert_gate": {
100
+ "group_size": 64,
101
+ "bits": 8
102
+ },
103
+ "language_model.model.layers.11.mlp.gate": {
104
+ "group_size": 64,
105
+ "bits": 8
106
+ },
107
+ "language_model.model.layers.11.mlp.shared_expert_gate": {
108
+ "group_size": 64,
109
+ "bits": 8
110
+ },
111
+ "language_model.model.layers.12.mlp.gate": {
112
+ "group_size": 64,
113
+ "bits": 8
114
+ },
115
+ "language_model.model.layers.12.mlp.shared_expert_gate": {
116
+ "group_size": 64,
117
+ "bits": 8
118
+ },
119
+ "language_model.model.layers.13.mlp.gate": {
120
+ "group_size": 64,
121
+ "bits": 8
122
+ },
123
+ "language_model.model.layers.13.mlp.shared_expert_gate": {
124
+ "group_size": 64,
125
+ "bits": 8
126
+ },
127
+ "language_model.model.layers.14.mlp.gate": {
128
+ "group_size": 64,
129
+ "bits": 8
130
+ },
131
+ "language_model.model.layers.14.mlp.shared_expert_gate": {
132
+ "group_size": 64,
133
+ "bits": 8
134
+ },
135
+ "language_model.model.layers.15.mlp.gate": {
136
+ "group_size": 64,
137
+ "bits": 8
138
+ },
139
+ "language_model.model.layers.15.mlp.shared_expert_gate": {
140
+ "group_size": 64,
141
+ "bits": 8
142
+ },
143
+ "language_model.model.layers.16.mlp.gate": {
144
+ "group_size": 64,
145
+ "bits": 8
146
+ },
147
+ "language_model.model.layers.16.mlp.shared_expert_gate": {
148
+ "group_size": 64,
149
+ "bits": 8
150
+ },
151
+ "language_model.model.layers.17.mlp.gate": {
152
+ "group_size": 64,
153
+ "bits": 8
154
+ },
155
+ "language_model.model.layers.17.mlp.shared_expert_gate": {
156
+ "group_size": 64,
157
+ "bits": 8
158
+ },
159
+ "language_model.model.layers.18.mlp.gate": {
160
+ "group_size": 64,
161
+ "bits": 8
162
+ },
163
+ "language_model.model.layers.18.mlp.shared_expert_gate": {
164
+ "group_size": 64,
165
+ "bits": 8
166
+ },
167
+ "language_model.model.layers.19.mlp.gate": {
168
+ "group_size": 64,
169
+ "bits": 8
170
+ },
171
+ "language_model.model.layers.19.mlp.shared_expert_gate": {
172
+ "group_size": 64,
173
+ "bits": 8
174
+ },
175
+ "language_model.model.layers.20.mlp.gate": {
176
+ "group_size": 64,
177
+ "bits": 8
178
+ },
179
+ "language_model.model.layers.20.mlp.shared_expert_gate": {
180
+ "group_size": 64,
181
+ "bits": 8
182
+ },
183
+ "language_model.model.layers.21.mlp.gate": {
184
+ "group_size": 64,
185
+ "bits": 8
186
+ },
187
+ "language_model.model.layers.21.mlp.shared_expert_gate": {
188
+ "group_size": 64,
189
+ "bits": 8
190
+ },
191
+ "language_model.model.layers.22.mlp.gate": {
192
+ "group_size": 64,
193
+ "bits": 8
194
+ },
195
+ "language_model.model.layers.22.mlp.shared_expert_gate": {
196
+ "group_size": 64,
197
+ "bits": 8
198
+ },
199
+ "language_model.model.layers.23.mlp.gate": {
200
+ "group_size": 64,
201
+ "bits": 8
202
+ },
203
+ "language_model.model.layers.23.mlp.shared_expert_gate": {
204
+ "group_size": 64,
205
+ "bits": 8
206
+ },
207
+ "language_model.model.layers.24.mlp.gate": {
208
+ "group_size": 64,
209
+ "bits": 8
210
+ },
211
+ "language_model.model.layers.24.mlp.shared_expert_gate": {
212
+ "group_size": 64,
213
+ "bits": 8
214
+ },
215
+ "language_model.model.layers.25.mlp.gate": {
216
+ "group_size": 64,
217
+ "bits": 8
218
+ },
219
+ "language_model.model.layers.25.mlp.shared_expert_gate": {
220
+ "group_size": 64,
221
+ "bits": 8
222
+ },
223
+ "language_model.model.layers.26.mlp.gate": {
224
+ "group_size": 64,
225
+ "bits": 8
226
+ },
227
+ "language_model.model.layers.26.mlp.shared_expert_gate": {
228
+ "group_size": 64,
229
+ "bits": 8
230
+ },
231
+ "language_model.model.layers.27.mlp.gate": {
232
+ "group_size": 64,
233
+ "bits": 8
234
+ },
235
+ "language_model.model.layers.27.mlp.shared_expert_gate": {
236
+ "group_size": 64,
237
+ "bits": 8
238
+ },
239
+ "language_model.model.layers.28.mlp.gate": {
240
+ "group_size": 64,
241
+ "bits": 8
242
+ },
243
+ "language_model.model.layers.28.mlp.shared_expert_gate": {
244
+ "group_size": 64,
245
+ "bits": 8
246
+ },
247
+ "language_model.model.layers.29.mlp.gate": {
248
+ "group_size": 64,
249
+ "bits": 8
250
+ },
251
+ "language_model.model.layers.29.mlp.shared_expert_gate": {
252
+ "group_size": 64,
253
+ "bits": 8
254
+ },
255
+ "language_model.model.layers.30.mlp.gate": {
256
+ "group_size": 64,
257
+ "bits": 8
258
+ },
259
+ "language_model.model.layers.30.mlp.shared_expert_gate": {
260
+ "group_size": 64,
261
+ "bits": 8
262
+ },
263
+ "language_model.model.layers.31.mlp.gate": {
264
+ "group_size": 64,
265
+ "bits": 8
266
+ },
267
+ "language_model.model.layers.31.mlp.shared_expert_gate": {
268
+ "group_size": 64,
269
+ "bits": 8
270
+ },
271
+ "language_model.model.layers.32.mlp.gate": {
272
+ "group_size": 64,
273
+ "bits": 8
274
+ },
275
+ "language_model.model.layers.32.mlp.shared_expert_gate": {
276
+ "group_size": 64,
277
+ "bits": 8
278
+ },
279
+ "language_model.model.layers.33.mlp.gate": {
280
+ "group_size": 64,
281
+ "bits": 8
282
+ },
283
+ "language_model.model.layers.33.mlp.shared_expert_gate": {
284
+ "group_size": 64,
285
+ "bits": 8
286
+ },
287
+ "language_model.model.layers.34.mlp.gate": {
288
+ "group_size": 64,
289
+ "bits": 8
290
+ },
291
+ "language_model.model.layers.34.mlp.shared_expert_gate": {
292
+ "group_size": 64,
293
+ "bits": 8
294
+ },
295
+ "language_model.model.layers.35.mlp.gate": {
296
+ "group_size": 64,
297
+ "bits": 8
298
+ },
299
+ "language_model.model.layers.35.mlp.shared_expert_gate": {
300
+ "group_size": 64,
301
+ "bits": 8
302
+ },
303
+ "language_model.model.layers.36.mlp.gate": {
304
+ "group_size": 64,
305
+ "bits": 8
306
+ },
307
+ "language_model.model.layers.36.mlp.shared_expert_gate": {
308
+ "group_size": 64,
309
+ "bits": 8
310
+ },
311
+ "language_model.model.layers.37.mlp.gate": {
312
+ "group_size": 64,
313
+ "bits": 8
314
+ },
315
+ "language_model.model.layers.37.mlp.shared_expert_gate": {
316
+ "group_size": 64,
317
+ "bits": 8
318
+ },
319
+ "language_model.model.layers.38.mlp.gate": {
320
+ "group_size": 64,
321
+ "bits": 8
322
+ },
323
+ "language_model.model.layers.38.mlp.shared_expert_gate": {
324
+ "group_size": 64,
325
+ "bits": 8
326
+ },
327
+ "language_model.model.layers.39.mlp.gate": {
328
+ "group_size": 64,
329
+ "bits": 8
330
+ },
331
+ "language_model.model.layers.39.mlp.shared_expert_gate": {
332
+ "group_size": 64,
333
+ "bits": 8
334
+ }
335
+ },
336
+ "quantization_config": {
337
+ "group_size": 64,
338
+ "bits": 6,
339
+ "mode": "affine",
340
+ "language_model.model.layers.0.mlp.gate": {
341
+ "group_size": 64,
342
+ "bits": 8
343
+ },
344
+ "language_model.model.layers.0.mlp.shared_expert_gate": {
345
+ "group_size": 64,
346
+ "bits": 8
347
+ },
348
+ "language_model.model.layers.1.mlp.gate": {
349
+ "group_size": 64,
350
+ "bits": 8
351
+ },
352
+ "language_model.model.layers.1.mlp.shared_expert_gate": {
353
+ "group_size": 64,
354
+ "bits": 8
355
+ },
356
+ "language_model.model.layers.2.mlp.gate": {
357
+ "group_size": 64,
358
+ "bits": 8
359
+ },
360
+ "language_model.model.layers.2.mlp.shared_expert_gate": {
361
+ "group_size": 64,
362
+ "bits": 8
363
+ },
364
+ "language_model.model.layers.3.mlp.gate": {
365
+ "group_size": 64,
366
+ "bits": 8
367
+ },
368
+ "language_model.model.layers.3.mlp.shared_expert_gate": {
369
+ "group_size": 64,
370
+ "bits": 8
371
+ },
372
+ "language_model.model.layers.4.mlp.gate": {
373
+ "group_size": 64,
374
+ "bits": 8
375
+ },
376
+ "language_model.model.layers.4.mlp.shared_expert_gate": {
377
+ "group_size": 64,
378
+ "bits": 8
379
+ },
380
+ "language_model.model.layers.5.mlp.gate": {
381
+ "group_size": 64,
382
+ "bits": 8
383
+ },
384
+ "language_model.model.layers.5.mlp.shared_expert_gate": {
385
+ "group_size": 64,
386
+ "bits": 8
387
+ },
388
+ "language_model.model.layers.6.mlp.gate": {
389
+ "group_size": 64,
390
+ "bits": 8
391
+ },
392
+ "language_model.model.layers.6.mlp.shared_expert_gate": {
393
+ "group_size": 64,
394
+ "bits": 8
395
+ },
396
+ "language_model.model.layers.7.mlp.gate": {
397
+ "group_size": 64,
398
+ "bits": 8
399
+ },
400
+ "language_model.model.layers.7.mlp.shared_expert_gate": {
401
+ "group_size": 64,
402
+ "bits": 8
403
+ },
404
+ "language_model.model.layers.8.mlp.gate": {
405
+ "group_size": 64,
406
+ "bits": 8
407
+ },
408
+ "language_model.model.layers.8.mlp.shared_expert_gate": {
409
+ "group_size": 64,
410
+ "bits": 8
411
+ },
412
+ "language_model.model.layers.9.mlp.gate": {
413
+ "group_size": 64,
414
+ "bits": 8
415
+ },
416
+ "language_model.model.layers.9.mlp.shared_expert_gate": {
417
+ "group_size": 64,
418
+ "bits": 8
419
+ },
420
+ "language_model.model.layers.10.mlp.gate": {
421
+ "group_size": 64,
422
+ "bits": 8
423
+ },
424
+ "language_model.model.layers.10.mlp.shared_expert_gate": {
425
+ "group_size": 64,
426
+ "bits": 8
427
+ },
428
+ "language_model.model.layers.11.mlp.gate": {
429
+ "group_size": 64,
430
+ "bits": 8
431
+ },
432
+ "language_model.model.layers.11.mlp.shared_expert_gate": {
433
+ "group_size": 64,
434
+ "bits": 8
435
+ },
436
+ "language_model.model.layers.12.mlp.gate": {
437
+ "group_size": 64,
438
+ "bits": 8
439
+ },
440
+ "language_model.model.layers.12.mlp.shared_expert_gate": {
441
+ "group_size": 64,
442
+ "bits": 8
443
+ },
444
+ "language_model.model.layers.13.mlp.gate": {
445
+ "group_size": 64,
446
+ "bits": 8
447
+ },
448
+ "language_model.model.layers.13.mlp.shared_expert_gate": {
449
+ "group_size": 64,
450
+ "bits": 8
451
+ },
452
+ "language_model.model.layers.14.mlp.gate": {
453
+ "group_size": 64,
454
+ "bits": 8
455
+ },
456
+ "language_model.model.layers.14.mlp.shared_expert_gate": {
457
+ "group_size": 64,
458
+ "bits": 8
459
+ },
460
+ "language_model.model.layers.15.mlp.gate": {
461
+ "group_size": 64,
462
+ "bits": 8
463
+ },
464
+ "language_model.model.layers.15.mlp.shared_expert_gate": {
465
+ "group_size": 64,
466
+ "bits": 8
467
+ },
468
+ "language_model.model.layers.16.mlp.gate": {
469
+ "group_size": 64,
470
+ "bits": 8
471
+ },
472
+ "language_model.model.layers.16.mlp.shared_expert_gate": {
473
+ "group_size": 64,
474
+ "bits": 8
475
+ },
476
+ "language_model.model.layers.17.mlp.gate": {
477
+ "group_size": 64,
478
+ "bits": 8
479
+ },
480
+ "language_model.model.layers.17.mlp.shared_expert_gate": {
481
+ "group_size": 64,
482
+ "bits": 8
483
+ },
484
+ "language_model.model.layers.18.mlp.gate": {
485
+ "group_size": 64,
486
+ "bits": 8
487
+ },
488
+ "language_model.model.layers.18.mlp.shared_expert_gate": {
489
+ "group_size": 64,
490
+ "bits": 8
491
+ },
492
+ "language_model.model.layers.19.mlp.gate": {
493
+ "group_size": 64,
494
+ "bits": 8
495
+ },
496
+ "language_model.model.layers.19.mlp.shared_expert_gate": {
497
+ "group_size": 64,
498
+ "bits": 8
499
+ },
500
+ "language_model.model.layers.20.mlp.gate": {
501
+ "group_size": 64,
502
+ "bits": 8
503
+ },
504
+ "language_model.model.layers.20.mlp.shared_expert_gate": {
505
+ "group_size": 64,
506
+ "bits": 8
507
+ },
508
+ "language_model.model.layers.21.mlp.gate": {
509
+ "group_size": 64,
510
+ "bits": 8
511
+ },
512
+ "language_model.model.layers.21.mlp.shared_expert_gate": {
513
+ "group_size": 64,
514
+ "bits": 8
515
+ },
516
+ "language_model.model.layers.22.mlp.gate": {
517
+ "group_size": 64,
518
+ "bits": 8
519
+ },
520
+ "language_model.model.layers.22.mlp.shared_expert_gate": {
521
+ "group_size": 64,
522
+ "bits": 8
523
+ },
524
+ "language_model.model.layers.23.mlp.gate": {
525
+ "group_size": 64,
526
+ "bits": 8
527
+ },
528
+ "language_model.model.layers.23.mlp.shared_expert_gate": {
529
+ "group_size": 64,
530
+ "bits": 8
531
+ },
532
+ "language_model.model.layers.24.mlp.gate": {
533
+ "group_size": 64,
534
+ "bits": 8
535
+ },
536
+ "language_model.model.layers.24.mlp.shared_expert_gate": {
537
+ "group_size": 64,
538
+ "bits": 8
539
+ },
540
+ "language_model.model.layers.25.mlp.gate": {
541
+ "group_size": 64,
542
+ "bits": 8
543
+ },
544
+ "language_model.model.layers.25.mlp.shared_expert_gate": {
545
+ "group_size": 64,
546
+ "bits": 8
547
+ },
548
+ "language_model.model.layers.26.mlp.gate": {
549
+ "group_size": 64,
550
+ "bits": 8
551
+ },
552
+ "language_model.model.layers.26.mlp.shared_expert_gate": {
553
+ "group_size": 64,
554
+ "bits": 8
555
+ },
556
+ "language_model.model.layers.27.mlp.gate": {
557
+ "group_size": 64,
558
+ "bits": 8
559
+ },
560
+ "language_model.model.layers.27.mlp.shared_expert_gate": {
561
+ "group_size": 64,
562
+ "bits": 8
563
+ },
564
+ "language_model.model.layers.28.mlp.gate": {
565
+ "group_size": 64,
566
+ "bits": 8
567
+ },
568
+ "language_model.model.layers.28.mlp.shared_expert_gate": {
569
+ "group_size": 64,
570
+ "bits": 8
571
+ },
572
+ "language_model.model.layers.29.mlp.gate": {
573
+ "group_size": 64,
574
+ "bits": 8
575
+ },
576
+ "language_model.model.layers.29.mlp.shared_expert_gate": {
577
+ "group_size": 64,
578
+ "bits": 8
579
+ },
580
+ "language_model.model.layers.30.mlp.gate": {
581
+ "group_size": 64,
582
+ "bits": 8
583
+ },
584
+ "language_model.model.layers.30.mlp.shared_expert_gate": {
585
+ "group_size": 64,
586
+ "bits": 8
587
+ },
588
+ "language_model.model.layers.31.mlp.gate": {
589
+ "group_size": 64,
590
+ "bits": 8
591
+ },
592
+ "language_model.model.layers.31.mlp.shared_expert_gate": {
593
+ "group_size": 64,
594
+ "bits": 8
595
+ },
596
+ "language_model.model.layers.32.mlp.gate": {
597
+ "group_size": 64,
598
+ "bits": 8
599
+ },
600
+ "language_model.model.layers.32.mlp.shared_expert_gate": {
601
+ "group_size": 64,
602
+ "bits": 8
603
+ },
604
+ "language_model.model.layers.33.mlp.gate": {
605
+ "group_size": 64,
606
+ "bits": 8
607
+ },
608
+ "language_model.model.layers.33.mlp.shared_expert_gate": {
609
+ "group_size": 64,
610
+ "bits": 8
611
+ },
612
+ "language_model.model.layers.34.mlp.gate": {
613
+ "group_size": 64,
614
+ "bits": 8
615
+ },
616
+ "language_model.model.layers.34.mlp.shared_expert_gate": {
617
+ "group_size": 64,
618
+ "bits": 8
619
+ },
620
+ "language_model.model.layers.35.mlp.gate": {
621
+ "group_size": 64,
622
+ "bits": 8
623
+ },
624
+ "language_model.model.layers.35.mlp.shared_expert_gate": {
625
+ "group_size": 64,
626
+ "bits": 8
627
+ },
628
+ "language_model.model.layers.36.mlp.gate": {
629
+ "group_size": 64,
630
+ "bits": 8
631
+ },
632
+ "language_model.model.layers.36.mlp.shared_expert_gate": {
633
+ "group_size": 64,
634
+ "bits": 8
635
+ },
636
+ "language_model.model.layers.37.mlp.gate": {
637
+ "group_size": 64,
638
+ "bits": 8
639
+ },
640
+ "language_model.model.layers.37.mlp.shared_expert_gate": {
641
+ "group_size": 64,
642
+ "bits": 8
643
+ },
644
+ "language_model.model.layers.38.mlp.gate": {
645
+ "group_size": 64,
646
+ "bits": 8
647
+ },
648
+ "language_model.model.layers.38.mlp.shared_expert_gate": {
649
+ "group_size": 64,
650
+ "bits": 8
651
+ },
652
+ "language_model.model.layers.39.mlp.gate": {
653
+ "group_size": 64,
654
+ "bits": 8
655
+ },
656
+ "language_model.model.layers.39.mlp.shared_expert_gate": {
657
+ "group_size": 64,
658
+ "bits": 8
659
+ }
660
+ },
661
+ "text_config": {
662
+ "attention_bias": false,
663
+ "attention_dropout": 0.0,
664
+ "attn_output_gate": true,
665
+ "bos_token_id": 248044,
666
+ "torch_dtype": "bfloat16",
667
+ "eos_token_id": 248044,
668
+ "full_attention_interval": 4,
669
+ "head_dim": 256,
670
+ "hidden_act": "silu",
671
+ "hidden_size": 2048,
672
+ "initializer_range": 0.02,
673
+ "layer_types": [
674
+ "linear_attention",
675
+ "linear_attention",
676
+ "linear_attention",
677
+ "full_attention",
678
+ "linear_attention",
679
+ "linear_attention",
680
+ "linear_attention",
681
+ "full_attention",
682
+ "linear_attention",
683
+ "linear_attention",
684
+ "linear_attention",
685
+ "full_attention",
686
+ "linear_attention",
687
+ "linear_attention",
688
+ "linear_attention",
689
+ "full_attention",
690
+ "linear_attention",
691
+ "linear_attention",
692
+ "linear_attention",
693
+ "full_attention",
694
+ "linear_attention",
695
+ "linear_attention",
696
+ "linear_attention",
697
+ "full_attention",
698
+ "linear_attention",
699
+ "linear_attention",
700
+ "linear_attention",
701
+ "full_attention",
702
+ "linear_attention",
703
+ "linear_attention",
704
+ "linear_attention",
705
+ "full_attention",
706
+ "linear_attention",
707
+ "linear_attention",
708
+ "linear_attention",
709
+ "full_attention",
710
+ "linear_attention",
711
+ "linear_attention",
712
+ "linear_attention",
713
+ "full_attention"
714
+ ],
715
+ "linear_conv_kernel_dim": 4,
716
+ "linear_key_head_dim": 128,
717
+ "linear_num_key_heads": 16,
718
+ "linear_num_value_heads": 32,
719
+ "linear_value_head_dim": 128,
720
+ "mamba_ssm_dtype": "float32",
721
+ "max_position_embeddings": 262144,
722
+ "model_type": "qwen3_5_moe_text",
723
+ "moe_intermediate_size": 512,
724
+ "mtp_num_hidden_layers": 1,
725
+ "mtp_use_dedicated_embeddings": false,
726
+ "num_attention_heads": 16,
727
+ "num_experts": 256,
728
+ "num_experts_per_tok": 8,
729
+ "num_hidden_layers": 40,
730
+ "num_key_value_heads": 2,
731
+ "output_router_logits": false,
732
+ "pad_token_id": null,
733
+ "partial_rotary_factor": 0.25,
734
+ "rms_norm_eps": 1e-06,
735
+ "rope_parameters": {
736
+ "mrope_interleaved": true,
737
+ "mrope_section": [
738
+ 11,
739
+ 11,
740
+ 10
741
+ ],
742
+ "partial_rotary_factor": 0.25,
743
+ "rope_theta": 10000000,
744
+ "type": "default"
745
+ },
746
+ "router_aux_loss_coef": 0.001,
747
+ "shared_expert_intermediate_size": 512,
748
+ "tie_word_embeddings": false,
749
+ "use_cache": true,
750
+ "vocab_size": 248320
751
+ },
752
+ "tie_word_embeddings": false,
753
+ "torch_dtype": "bfloat16",
754
+ "unsloth_version": "2026.4.1",
755
+ "use_cache": false,
756
+ "video_token_id": 248057,
757
+ "vision_end_token_id": 248054,
758
+ "vision_start_token_id": 248053
759
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1389116921e89c4d7adf9d29ad74385ac808b3a67ee435bf53322c6517b29b89
3
+ size 5224773925
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efdbbacb47ae47fe5f0b3d694f2580fc9051c7c08f9a5c1eca4b3527c97d7d27
3
+ size 5225058031
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373cdf356f92642199a5a4d0cab341c32ab5476c2a32876477e63db1a6faeeb0
3
+ size 5250337810
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8336b1c1ba2a7175719f1e42e242fb52eee90ce047c71cb9f06847f697131bdf
3
+ size 5250337542
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610338f107f3f3c74af3da10961559a2452d5967e46ea574518bec3c2bc8f72e
3
+ size 5219774304
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed96009db90bcb06923f82af2792b1a19e53db4d304c4c4e15601b77e713f8ca
3
+ size 1998341507
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|vision_pad|>",
24
+ "padding_side": "right",
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
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "tool_parser_type": "qwen3_coder",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }