Hugging Face's logo

cudo528
/
Darwin-28B-Coder-mlx-8bit

Text Generation
MLX
Safetensors
English
Korean
qwen3_5
code
code-generation
function-calling
darwin
conversational
8-bit precision
Model card Files
xet
 Community
cudo528 commited on
Commit
a2c6c6a
·
verified ·
1 Parent(s): da3c70e

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. README.md +17 -0
  3. chat_template.jinja +88 -0
  4. config.json +143 -0
  5. generation_config.json +12 -0
  6. model-00001-of-00006.safetensors +3 -0
  7. model-00002-of-00006.safetensors +3 -0
  8. model-00003-of-00006.safetensors +3 -0
  9. model-00004-of-00006.safetensors +3 -0
  10. model-00005-of-00006.safetensors +3 -0
  11. model-00006-of-00006.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
  13. tokenizer.json +3 -0
  14. 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 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: mlx
4
+ pipeline_tag: text-generation
5
+ language:
6
+ - en
7
+ - ko
8
+ tags:
9
+ - code
10
+ - code-generation
11
+ - function-calling
12
+ - darwin
13
+ - mlx
14
+ base_model: FINAL-Bench/Darwin-28B-Coder
15
+ datasets:
16
+ - m-a-p/CodeFeedback-Filtered-Instruction
17
+ ---
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 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "eos_token_id": [
7
+ 248046,
8
+ 248044
9
+ ],
10
+ "image_token_id": 248056,
11
+ "language_model_only": false,
12
+ "model_name": "unsloth/Qwen3.6-27B",
13
+ "model_type": "qwen3_5",
14
+ "pad_token_id": 248055,
15
+ "quantization": {
16
+ "group_size": 64,
17
+ "bits": 8,
18
+ "mode": "affine"
19
+ },
20
+ "quantization_config": {
21
+ "group_size": 64,
22
+ "bits": 8,
23
+ "mode": "affine"
24
+ },
25
+ "text_config": {
26
+ "attention_bias": false,
27
+ "attention_dropout": 0.0,
28
+ "attn_output_gate": true,
29
+ "bos_token_id": 248044,
30
+ "torch_dtype": "bfloat16",
31
+ "eos_token_id": 248044,
32
+ "full_attention_interval": 4,
33
+ "head_dim": 256,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 5120,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 17408,
38
+ "layer_types": [
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
+ "linear_attention",
100
+ "linear_attention",
101
+ "linear_attention",
102
+ "full_attention"
103
+ ],
104
+ "linear_conv_kernel_dim": 4,
105
+ "linear_key_head_dim": 128,
106
+ "linear_num_key_heads": 16,
107
+ "linear_num_value_heads": 48,
108
+ "linear_value_head_dim": 128,
109
+ "mamba_ssm_dtype": "float32",
110
+ "max_position_embeddings": 262144,
111
+ "model_type": "qwen3_5_text",
112
+ "mtp_num_hidden_layers": 1,
113
+ "mtp_use_dedicated_embeddings": false,
114
+ "num_attention_heads": 24,
115
+ "num_hidden_layers": 64,
116
+ "num_key_value_heads": 4,
117
+ "output_gate_type": "swish",
118
+ "pad_token_id": null,
119
+ "partial_rotary_factor": 0.25,
120
+ "rms_norm_eps": 1e-06,
121
+ "rope_parameters": {
122
+ "mrope_interleaved": true,
123
+ "mrope_section": [
124
+ 11,
125
+ 11,
126
+ 10
127
+ ],
128
+ "partial_rotary_factor": 0.25,
129
+ "rope_theta": 10000000,
130
+ "type": "default"
131
+ },
132
+ "tie_word_embeddings": false,
133
+ "use_cache": true,
134
+ "vocab_size": 248320
135
+ },
136
+ "tie_word_embeddings": false,
137
+ "torch_dtype": "bfloat16",
138
+ "unsloth_version": "2026.4.7",
139
+ "use_cache": false,
140
+ "video_token_id": 248057,
141
+ "vision_end_token_id": 248054,
142
+ "vision_start_token_id": 248053
143
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0feedc00467d377432fdd6d34dcbf67871eca1bb302ba0d40deb506da09a513a
3
+ size 5305469313
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a12d16e3e476d83caca99c6f594138fa2838da63d08cff93885078b3ec15174
3
+ size 5354102628
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39309de8e13d03e6ca93ba1bcc65618a63bca49444c848843c927625dd332e61
3
+ size 5337392986
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f855697e71b5b7120cb115fdabc693d54c11af6a9ff68e8e8ebb30a1625a62de
3
+ size 5292847128
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b11913ab4e9877bf4903e3487d1e036201fc50b7df937cd256b50d08f6b094
3
+ size 5354102635
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4beb88c6222e83fcf31511f286e79c96bb515dd4de0b753f52bb59b5ebec820
3
+ size 1935805825
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
+ }