Hugging Face's logo

nom666
/
Qwopus3.6-27B-Coder-MTPLX-4bit-Speed

Text Generation
MLX
Safetensors
English
qwen3_5
mtplx
mtp
speculative-decoding
apple-silicon
qwopus
code
agent
conversational
4-bit precision
Model card Files
xet
 Community
nom666 commited on
Commit
4f23bee
·
verified ·
1 Parent(s): be357bd

Publish MTPLX forged model

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +7 -0
  3. chat_template.jinja +158 -0
  4. config.json +165 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00003.safetensors +3 -0
  7. model-00002-of-00003.safetensors +3 -0
  8. model-00003-of-00003.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. mtp.safetensors +3 -0
  11. mtplx_runtime.json +137 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +35 -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 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ pipeline_tag: text-generation
4
+ library_name: mlx
5
+ tags:
6
+ - mlx
7
+ ---
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 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "eos_token_id": [
6
+ 248046,
7
+ 248044
8
+ ],
9
+ "image_token_id": 248056,
10
+ "language_model_only": false,
11
+ "mlx_lm_extra_tensors": {
12
+ "mtp_file": "mtp.safetensors"
13
+ },
14
+ "model_name": "Unsloth/qwen3.6-27B",
15
+ "model_type": "qwen3_5",
16
+ "mtp_num_hidden_layers": 1,
17
+ "mtplx_mtp_contract": {
18
+ "base_hidden_variant": "post_norm",
19
+ "concat_order": "embedding_hidden",
20
+ "hidden_variant": "post_norm",
21
+ "mtp_position_mode": "local",
22
+ "mtp_quant_group_size": 64,
23
+ "mtp_quant_mode": "affine"
24
+ },
25
+ "mtplx_mtp_payload_audit": {
26
+ "mtp_file": "/Users/nomish/.mtplx/models/Qwopus3.6-27B-Coder-MTPLX-4bit-Speed/mtp.safetensors",
27
+ "nonzero_payload_tensor_count": 8,
28
+ "passed": true,
29
+ "payload_tensor_count": 8,
30
+ "problems": [],
31
+ "scale_tensor_count": 0,
32
+ "tensor_count": 15,
33
+ "zero_payload_sample": [],
34
+ "zero_scale_sample": []
35
+ },
36
+ "pad_token_id": 248055,
37
+ "quantization": {
38
+ "bits": 4,
39
+ "group_size": 64,
40
+ "mode": "affine"
41
+ },
42
+ "quantization_config": {
43
+ "bits": 4,
44
+ "group_size": 64,
45
+ "mode": "affine"
46
+ },
47
+ "text_config": {
48
+ "attention_bias": false,
49
+ "attention_dropout": 0.0,
50
+ "attn_output_gate": true,
51
+ "bos_token_id": 248044,
52
+ "eos_token_id": 248044,
53
+ "full_attention_interval": 4,
54
+ "head_dim": 256,
55
+ "hidden_act": "silu",
56
+ "hidden_size": 5120,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 17408,
59
+ "layer_types": [
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "full_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "full_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "full_attention",
92
+ "linear_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "full_attention",
96
+ "linear_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "full_attention",
100
+ "linear_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "full_attention",
104
+ "linear_attention",
105
+ "linear_attention",
106
+ "linear_attention",
107
+ "full_attention",
108
+ "linear_attention",
109
+ "linear_attention",
110
+ "linear_attention",
111
+ "full_attention",
112
+ "linear_attention",
113
+ "linear_attention",
114
+ "linear_attention",
115
+ "full_attention",
116
+ "linear_attention",
117
+ "linear_attention",
118
+ "linear_attention",
119
+ "full_attention",
120
+ "linear_attention",
121
+ "linear_attention",
122
+ "linear_attention",
123
+ "full_attention"
124
+ ],
125
+ "linear_conv_kernel_dim": 4,
126
+ "linear_key_head_dim": 128,
127
+ "linear_num_key_heads": 16,
128
+ "linear_num_value_heads": 48,
129
+ "linear_value_head_dim": 128,
130
+ "mamba_ssm_dtype": "float32",
131
+ "max_position_embeddings": 262144,
132
+ "model_type": "qwen3_5_text",
133
+ "mtp_num_hidden_layers": 1,
134
+ "mtp_use_dedicated_embeddings": false,
135
+ "num_attention_heads": 24,
136
+ "num_hidden_layers": 64,
137
+ "num_key_value_heads": 4,
138
+ "output_gate_type": "swish",
139
+ "pad_token_id": null,
140
+ "partial_rotary_factor": 0.25,
141
+ "rms_norm_eps": 1e-06,
142
+ "rope_parameters": {
143
+ "mrope_interleaved": true,
144
+ "mrope_section": [
145
+ 11,
146
+ 11,
147
+ 10
148
+ ],
149
+ "partial_rotary_factor": 0.25,
150
+ "rope_theta": 10000000,
151
+ "type": "default"
152
+ },
153
+ "tie_word_embeddings": false,
154
+ "torch_dtype": "bfloat16",
155
+ "use_cache": true,
156
+ "vocab_size": 248320
157
+ },
158
+ "tie_word_embeddings": false,
159
+ "torch_dtype": "bfloat16",
160
+ "unsloth_fixed_mtp": true,
161
+ "unsloth_version": "2026.5.9",
162
+ "video_token_id": 248057,
163
+ "vision_end_token_id": 248054,
164
+ "vision_start_token_id": 248053
165
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248055,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.3.0"
13
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d8807bc113528c03adf515e6f7550f19ae20eb4fe8ac35eb9fb43bdac3e9f5
3
+ size 5328325648
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0297fc592907041fb428aaa4688de2c6fc5b9f130e76f9807a393415d85b89c8
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:be22c13155a74aea225e936d45d5b648f6ebbca138d8f4052e8a4bdb211d6424
3
+ size 4450532735
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94046b581f47f52e378fc7122833d7ba751231565915a9059286401dd9bbb9d
3
+ size 849400389
mtplx_runtime.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "arch_id": "qwen3-next-mtp",
3
+ "artifact_role": "forge-local",
4
+ "base_trunk": "Jackrong/Qwopus3.6-27B-Coder",
5
+ "exactness_baseline": {},
6
+ "forge_provenance": {
7
+ "forge_inputs": {
8
+ "mtp_source_path": "/Users/nomish/.mtplx/models/Jackrong--Qwopus3.6-27B-Coder",
9
+ "trunk_path": "/Users/nomish/.mtplx/models/Qwopus3.6-27B-Coder-MTPLX-4bit-Speed"
10
+ },
11
+ "forge_recipe": {
12
+ "body_bits": 4,
13
+ "body_group_size": 64,
14
+ "body_mode": "affine",
15
+ "mtp_policy": "keep_bf16"
16
+ },
17
+ "forged_at": "2026-06-11T23:13:49-07:00",
18
+ "forged_locally": true,
19
+ "mtp_contract": {
20
+ "base_hidden_variant": "post_norm",
21
+ "concat_order": "embedding_hidden",
22
+ "hidden_variant": "post_norm",
23
+ "mtp_position_mode": "local",
24
+ "mtp_quant_group_size": 64,
25
+ "mtp_quant_mode": "affine"
26
+ },
27
+ "mtplx_version": "1.0.3",
28
+ "published_to_hf": null,
29
+ "source_format": "bf16_native",
30
+ "source_repo": "Jackrong/Qwopus3.6-27B-Coder",
31
+ "source_sha": "f22041be82998a006c9fde642c7900fb42aff94e"
32
+ },
33
+ "mtp_contract": {
34
+ "base_hidden_variant": "post_norm",
35
+ "concat_order": "embedding_hidden",
36
+ "hidden_variant": "post_norm",
37
+ "mtp_position_mode": "local",
38
+ "mtp_quant_group_size": 64,
39
+ "mtp_quant_mode": "affine"
40
+ },
41
+ "mtp_depth_max": 3,
42
+ "mtp_sidecar": "bf16",
43
+ "mtplx_version": "1.0.3",
44
+ "recommended_profile": "sustained",
45
+ "sampler": {
46
+ "temperature": 0.6,
47
+ "top_k": 20,
48
+ "top_p": 0.95
49
+ },
50
+ "speed_evidence": {
51
+ "acceptance_by_depth": [
52
+ 0.9666666666666667,
53
+ 0.9
54
+ ],
55
+ "acceptance_collapsed": [],
56
+ "depth": 2,
57
+ "failure_reasons": [],
58
+ "forge_verify_rows": [
59
+ {
60
+ "acceptance_by_position": [],
61
+ "depth": 0,
62
+ "finish_reasons": {
63
+ "stop": 1
64
+ },
65
+ "hit_token_budget": false,
66
+ "hit_token_budget_count": 0,
67
+ "multiplier_vs_ar": 1.0,
68
+ "quality_passed": true,
69
+ "tok_s": 26.772683533011488,
70
+ "verify_time_s": 17.554934083018452
71
+ },
72
+ {
73
+ "acceptance_by_position": [
74
+ 0.9743589743589743
75
+ ],
76
+ "depth": 1,
77
+ "finish_reasons": {
78
+ "stop": 1
79
+ },
80
+ "hit_token_budget": false,
81
+ "hit_token_budget_count": 0,
82
+ "multiplier_vs_ar": 1.8715195933471693,
83
+ "quality_passed": true,
84
+ "tok_s": 50.105601798514115,
85
+ "verify_time_s": 8.369772406760603
86
+ },
87
+ {
88
+ "acceptance_by_position": [
89
+ 0.9666666666666667,
90
+ 0.9
91
+ ],
92
+ "depth": 2,
93
+ "finish_reasons": {
94
+ "stop": 1
95
+ },
96
+ "hit_token_budget": false,
97
+ "hit_token_budget_count": 0,
98
+ "multiplier_vs_ar": 2.1393948460484173,
99
+ "quality_passed": true,
100
+ "tok_s": 57.27734116541011,
101
+ "verify_time_s": 5.123491415753961
102
+ },
103
+ {
104
+ "acceptance_by_position": [
105
+ 0.8953488372093024,
106
+ 0.7790697674418605,
107
+ 0.6976744186046512
108
+ ],
109
+ "depth": 3,
110
+ "finish_reasons": {
111
+ "stop": 1
112
+ },
113
+ "hit_token_budget": false,
114
+ "hit_token_budget_count": 0,
115
+ "multiplier_vs_ar": 2.0360891172535878,
116
+ "quality_passed": true,
117
+ "tok_s": 54.51156958123902,
118
+ "verify_time_s": 4.41023363545537
119
+ }
120
+ ],
121
+ "greedy_diagnostic": {
122
+ "tok_s": 26.772683533011488
123
+ },
124
+ "quality_rejected": [],
125
+ "tok_s": [
126
+ 57.27734116541011
127
+ ],
128
+ "verdict": "mtp_depth_wins"
129
+ },
130
+ "verified_on": {
131
+ "hardware": "macOS-26.4.1-arm64-arm-64bit-Mach-O",
132
+ "machine_arch": "arm64",
133
+ "macos": "26.4.1",
134
+ "model": "Qwopus3.6-27B-Coder-MTPLX-4bit-Speed",
135
+ "timestamp": "2026-06-11T23:13:49-07:00"
136
+ }
137
+ }
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": "left",
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
+ "tool_parser_type": "qwen3_coder",
31
+ "unk_token": null,
32
+ "video_token": "<|video_pad|>",
33
+ "vision_bos_token": "<|vision_start|>",
34
+ "vision_eos_token": "<|vision_end|>"
35
+ }