Hugging Face's logo

jing96963
/
Huihui-Qwen3-6-35B-A3B-FP8-DYNAMIC

Safetensors
qwen3_5_moe_text
compressed-tensors
Model card Files
xet
 Community
jing96963 commited on
Commit
f2b9ee6
·
verified ·
1 Parent(s): c086eb3

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +158 -0
  3. config.json +145 -0
  4. generation_config.json +8 -0
  5. model-00001-of-00002.safetensors +3 -0
  6. model-00002-of-00002.safetensors +3 -0
  7. model.safetensors.index.json +0 -0
  8. recipe.yaml +7 -0
  9. tokenizer.json +3 -0
  10. 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
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 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_output_gate": true,
8
+ "bos_token_id": 248044,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 248044,
11
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "layer_types": [
17
+ "linear_attention",
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "full_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention"
57
+ ],
58
+ "linear_conv_kernel_dim": 4,
59
+ "linear_key_head_dim": 128,
60
+ "linear_num_key_heads": 16,
61
+ "linear_num_value_heads": 32,
62
+ "linear_value_head_dim": 128,
63
+ "mamba_ssm_dtype": "float32",
64
+ "max_position_embeddings": 262144,
65
+ "model_type": "qwen3_5_moe_text",
66
+ "moe_intermediate_size": 512,
67
+ "mtp_num_hidden_layers": 1,
68
+ "mtp_use_dedicated_embeddings": false,
69
+ "num_attention_heads": 16,
70
+ "num_experts": 256,
71
+ "num_experts_per_tok": 8,
72
+ "num_hidden_layers": 40,
73
+ "num_key_value_heads": 2,
74
+ "output_router_logits": false,
75
+ "pad_token_id": null,
76
+ "partial_rotary_factor": 0.25,
77
+ "quantization_config": {
78
+ "config_groups": {
79
+ "group_0": {
80
+ "format": "float-quantized",
81
+ "input_activations": {
82
+ "actorder": null,
83
+ "block_structure": null,
84
+ "dynamic": true,
85
+ "group_size": null,
86
+ "num_bits": 8,
87
+ "observer": null,
88
+ "observer_kwargs": {},
89
+ "scale_dtype": null,
90
+ "strategy": "token",
91
+ "symmetric": true,
92
+ "type": "float",
93
+ "zp_dtype": null
94
+ },
95
+ "output_activations": null,
96
+ "targets": [
97
+ "Linear"
98
+ ],
99
+ "weights": {
100
+ "actorder": null,
101
+ "block_structure": null,
102
+ "dynamic": false,
103
+ "group_size": null,
104
+ "num_bits": 8,
105
+ "observer": "memoryless_minmax",
106
+ "observer_kwargs": {},
107
+ "scale_dtype": null,
108
+ "strategy": "channel",
109
+ "symmetric": true,
110
+ "type": "float",
111
+ "zp_dtype": null
112
+ }
113
+ }
114
+ },
115
+ "format": "float-quantized",
116
+ "global_compression_ratio": null,
117
+ "ignore": [
118
+ "lm_head"
119
+ ],
120
+ "kv_cache_scheme": null,
121
+ "quant_method": "compressed-tensors",
122
+ "quantization_status": "compressed",
123
+ "sparsity_config": {},
124
+ "transform_config": {},
125
+ "version": "0.14.0.1"
126
+ },
127
+ "rms_norm_eps": 1e-06,
128
+ "rope_parameters": {
129
+ "mrope_interleaved": true,
130
+ "mrope_section": [
131
+ 11,
132
+ 11,
133
+ 10
134
+ ],
135
+ "partial_rotary_factor": 0.25,
136
+ "rope_theta": 10000000,
137
+ "rope_type": "default"
138
+ },
139
+ "router_aux_loss_coef": 0.001,
140
+ "shared_expert_intermediate_size": 512,
141
+ "tie_word_embeddings": false,
142
+ "transformers_version": "5.7.0.dev0",
143
+ "use_cache": true,
144
+ "vocab_size": 248320
145
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 248044,
4
+ "eos_token_id": 248046,
5
+ "pad_token_id": 248055,
6
+ "transformers_version": "5.7.0.dev0",
7
+ "use_cache": false
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ebd6103ff0b172e0ff2724eb05ce57d1e4ba46e8a915c722c4344d40236ee3
3
+ size 49832178946
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25733726a543e20d966f0fca193ce7e3a0f0e314573534edaedb667d1d10d5e
3
+ size 18081416470
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*mlp.gate$']
6
+ scheme: FP8_DYNAMIC
7
+ bypass_divisibility_checks: false
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": false,
13
+ "local_files_only": false,
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": "<|vision_pad|>",
25
+ "padding_side": "right",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "TokenizersBackend",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }