Hugging Face's logo

Jackrong
/
MLX-Qwopus3.5-27B-v3-4bit

Text Generation
MLX
Safetensors
English
Chinese
Korean
qwen3_5
unsloth
qwen
qwen3.5
reasoning
chain-of-thought
lora
competitive-programming
conversational
4-bit precision
Model card Files
xet
 Community
1
Jackrong commited on
Commit
d399209
·
verified ·
1 Parent(s): a103f93

Add files using upload-large-folder tool

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. README.md +47 -0
  3. chat_template.jinja +88 -0
  4. config.json +140 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +0 -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
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - zh
5
+ - ko
6
+ license: apache-2.0
7
+ base_model: Jackrong/Qwopus3.5-27B-v3
8
+ tags:
9
+ - unsloth
10
+ - qwen
11
+ - qwen3.5
12
+ - reasoning
13
+ - chain-of-thought
14
+ - lora
15
+ - competitive-programming
16
+ - mlx
17
+ pipeline_tag: text-generation
18
+ library_name: mlx
19
+ ---
20
+
21
+ # Jackrong/MLX-Qwopus3.5-27B-v3-4bit
22
+
23
+ This model [Jackrong/MLX-Qwopus3.5-27B-v3-4bit](https://huggingface.co/Jackrong/MLX-Qwopus3.5-27B-v3-4bit) was
24
+ converted to MLX format from [Jackrong/Qwopus3.5-27B-v3](https://huggingface.co/Jackrong/Qwopus3.5-27B-v3)
25
+ using mlx-lm version **0.30.7**.
26
+
27
+ ## Use with mlx
28
+
29
+ ```bash
30
+ pip install mlx-lm
31
+ ```
32
+
33
+ ```python
34
+ from mlx_lm import load, generate
35
+
36
+ model, tokenizer = load("Jackrong/MLX-Qwopus3.5-27B-v3-4bit")
37
+
38
+ prompt = "hello"
39
+
40
+ if tokenizer.chat_template is not None:
41
+ messages = [{"role": "user", "content": prompt}]
42
+ prompt = tokenizer.apply_chat_template(
43
+ messages, add_generation_prompt=True, return_dict=False,
44
+ )
45
+
46
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
47
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant
86
+ <think>
87
+ ' }}
88
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "unsloth/Qwen3.5-27B",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248055,
11
+ "quantization": {
12
+ "group_size": 64,
13
+ "bits": 4,
14
+ "mode": "affine"
15
+ },
16
+ "quantization_config": {
17
+ "group_size": 64,
18
+ "bits": 4,
19
+ "mode": "affine"
20
+ },
21
+ "text_config": {
22
+ "attention_bias": false,
23
+ "attention_dropout": 0.0,
24
+ "attn_output_gate": true,
25
+ "bos_token_id": null,
26
+ "torch_dtype": "bfloat16",
27
+ "eos_token_id": 248044,
28
+ "full_attention_interval": 4,
29
+ "head_dim": 256,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 5120,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 17408,
34
+ "layer_types": [
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "full_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "full_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "full_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "full_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "full_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "full_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "full_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "full_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "full_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "full_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "full_attention",
91
+ "linear_attention",
92
+ "linear_attention",
93
+ "linear_attention",
94
+ "full_attention",
95
+ "linear_attention",
96
+ "linear_attention",
97
+ "linear_attention",
98
+ "full_attention"
99
+ ],
100
+ "linear_conv_kernel_dim": 4,
101
+ "linear_key_head_dim": 128,
102
+ "linear_num_key_heads": 16,
103
+ "linear_num_value_heads": 48,
104
+ "linear_value_head_dim": 128,
105
+ "mamba_ssm_dtype": "float32",
106
+ "max_position_embeddings": 262144,
107
+ "mlp_only_layers": [],
108
+ "model_type": "qwen3_5_text",
109
+ "mtp_num_hidden_layers": 1,
110
+ "mtp_use_dedicated_embeddings": false,
111
+ "num_attention_heads": 24,
112
+ "num_hidden_layers": 64,
113
+ "num_key_value_heads": 4,
114
+ "pad_token_id": null,
115
+ "partial_rotary_factor": 0.25,
116
+ "rms_norm_eps": 1e-06,
117
+ "rope_parameters": {
118
+ "mrope_interleaved": true,
119
+ "mrope_section": [
120
+ 11,
121
+ 11,
122
+ 10
123
+ ],
124
+ "partial_rotary_factor": 0.25,
125
+ "rope_theta": 10000000,
126
+ "type": "default"
127
+ },
128
+ "tie_word_embeddings": false,
129
+ "use_cache": true,
130
+ "vocab_size": 248320
131
+ },
132
+ "tie_word_embeddings": false,
133
+ "torch_dtype": "bfloat16",
134
+ "unsloth_fixed": true,
135
+ "unsloth_version": "2026.3.18",
136
+ "use_cache": false,
137
+ "video_token_id": 248057,
138
+ "vision_end_token_id": 248054,
139
+ "vision_start_token_id": 248053
140
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa79b2594e78378d491c7b582ff832b483264818301c825cc5c21cc203db2a4a
3
+ size 5328325648
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d1504ad2534cf2f98a0b8f26ffea5331b00d3d949b10820a0ace2b6ef964d9
3
+ size 5354185130
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd387be495bbb3b280e30182af966f3a6e6bc385b3229e5637ad4dfa2ab97da
3
+ size 4450532735
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": "json_tools",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }