Hugging Face's logo

codeclimber
/
Affine-5fwkxsjzzk-e5

Safetensors
qwen3_next
compressed-tensors
Model card Files
xet
 Community
codeclimber commited on
Commit
248f730
·
verified ·
1 Parent(s): ba8f79b

affine sn120 challenger: ckpt-92 fp8

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +117 -0
  3. config.json +195 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00002.safetensors +3 -0
  6. model-00002-of-00002.safetensors +3 -0
  7. model.safetensors.index.json +3 -0
  8. recipe.yaml +7 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +30 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% macro render_extra_keys(json_dict, handled_keys) %}
2
+ {%- if json_dict is mapping %}
3
+ {%- for json_key in json_dict if json_key not in handled_keys %}
4
+ {%- if json_dict[json_key] is string %}
5
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
6
+ {%- else %}
7
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
8
+ {%- endif %}
9
+ {%- endfor %}
10
+ {%- endif %}
11
+ {%- endmacro %}
12
+
13
+ {%- if messages[0]["role"] == "system" %}
14
+ {%- set system_message = messages[0]["content"] %}
15
+ {%- set loop_messages = messages[1:] %}
16
+ {%- else %}
17
+ {%- set loop_messages = messages %}
18
+ {%- endif %}
19
+
20
+ {%- if not tools is defined %}
21
+ {%- set tools = [] %}
22
+ {%- endif %}
23
+
24
+ {%- if system_message is defined %}
25
+ {{- "<|im_start|>system\n" + system_message }}
26
+ {%- else %}
27
+ {%- if tools is iterable and tools | length > 0 %}
28
+ {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- if tools is iterable and tools | length > 0 %}
32
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
33
+ {{- "<tools>" }}
34
+ {%- for tool in tools %}
35
+ {%- if tool.function is defined %}
36
+ {%- set tool = tool.function %}
37
+ {%- endif %}
38
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
39
+ {%- if tool.description is defined %}
40
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
41
+ {%- endif %}
42
+ {{- '\n<parameters>' }}
43
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
44
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
45
+ {{- '\n<parameter>' }}
46
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
47
+ {%- if param_fields.type is defined %}
48
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
49
+ {%- endif %}
50
+ {%- if param_fields.description is defined %}
51
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
52
+ {%- endif %}
53
+ {%- set handled_keys = ['name', 'type', 'description'] %}
54
+ {{- render_extra_keys(param_fields, handled_keys) }}
55
+ {{- '\n</parameter>' }}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {%- set handled_keys = ['type', 'properties'] %}
59
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
60
+ {{- '\n</parameters>' }}
61
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
62
+ {{- render_extra_keys(tool, handled_keys) }}
63
+ {{- '\n</function>' }}
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
+ {%- endif %}
68
+ {%- if system_message is defined %}
69
+ {{- '<|im_end|>\n' }}
70
+ {%- else %}
71
+ {%- if tools is iterable and tools | length > 0 %}
72
+ {{- '<|im_end|>\n' }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {%- for message in loop_messages %}
76
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
77
+ {{- '<|im_start|>' + message.role }}
78
+ {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
79
+ {{- '\n' + message.content | trim + '\n' }}
80
+ {%- endif %}
81
+ {%- for tool_call in message.tool_calls %}
82
+ {%- if tool_call.function is defined %}
83
+ {%- set tool_call = tool_call.function %}
84
+ {%- endif %}
85
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
86
+ {%- if tool_call.arguments is defined %}
87
+ {%- for args_name, args_value in tool_call.arguments|items %}
88
+ {{- '<parameter=' + args_name + '>\n' }}
89
+ {%- set args_value = args_value if args_value is string else args_value | tojson | safe %}
90
+ {{- args_value }}
91
+ {{- '\n</parameter>\n' }}
92
+ {%- endfor %}
93
+ {%- endif %}
94
+ {{- '</function>\n</tool_call>' }}
95
+ {%- endfor %}
96
+ {{- '<|im_end|>\n' }}
97
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
98
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
99
+ {%- elif message.role == "tool" %}
100
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
101
+ {{- '<|im_start|>user' }}
102
+ {%- endif %}
103
+ {{- '\n<tool_response>\n' }}
104
+ {{- message.content }}
105
+ {{- '\n</tool_response>' }}
106
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
107
+ {{- '<|im_end|>\n' }}
108
+ {%- elif loop.last %}
109
+ {{- '<|im_end|>\n' }}
110
+ {%- endif %}
111
+ {%- else %}
112
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
113
+ {%- endif %}
114
+ {%- endfor %}
115
+ {%- if add_generation_prompt %}
116
+ {{- '<|im_start|>assistant\n' }}
117
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3NextForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "head_dim": 256,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 5120,
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
+ "linear_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "full_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "full_attention"
65
+ ],
66
+ "linear_conv_kernel_dim": 4,
67
+ "linear_key_head_dim": 128,
68
+ "linear_num_key_heads": 16,
69
+ "linear_num_value_heads": 32,
70
+ "linear_value_head_dim": 128,
71
+ "max_position_embeddings": 262144,
72
+ "mlp_only_layers": [],
73
+ "model_type": "qwen3_next",
74
+ "moe_intermediate_size": 512,
75
+ "norm_topk_prob": true,
76
+ "num_attention_heads": 16,
77
+ "num_experts": 512,
78
+ "num_experts_per_tok": 10,
79
+ "num_hidden_layers": 48,
80
+ "num_key_value_heads": 2,
81
+ "output_router_logits": false,
82
+ "pad_token_id": null,
83
+ "partial_rotary_factor": 0.25,
84
+ "quantization_config": {
85
+ "config_groups": {
86
+ "group_0": {
87
+ "format": "float-quantized",
88
+ "input_activations": {
89
+ "actorder": null,
90
+ "block_structure": null,
91
+ "dynamic": true,
92
+ "group_size": null,
93
+ "num_bits": 8,
94
+ "observer": null,
95
+ "observer_kwargs": {},
96
+ "scale_dtype": null,
97
+ "strategy": "token",
98
+ "symmetric": true,
99
+ "type": "float",
100
+ "zp_dtype": null
101
+ },
102
+ "output_activations": null,
103
+ "targets": [
104
+ "Linear"
105
+ ],
106
+ "weights": {
107
+ "actorder": null,
108
+ "block_structure": null,
109
+ "dynamic": false,
110
+ "group_size": null,
111
+ "num_bits": 8,
112
+ "observer": "memoryless_minmax",
113
+ "observer_kwargs": {},
114
+ "scale_dtype": null,
115
+ "strategy": "channel",
116
+ "symmetric": true,
117
+ "type": "float",
118
+ "zp_dtype": null
119
+ }
120
+ }
121
+ },
122
+ "format": "float-quantized",
123
+ "global_compression_ratio": null,
124
+ "ignore": [
125
+ "model.layers.0.mlp.shared_expert_gate",
126
+ "model.layers.1.mlp.shared_expert_gate",
127
+ "model.layers.2.mlp.shared_expert_gate",
128
+ "model.layers.3.mlp.shared_expert_gate",
129
+ "model.layers.4.mlp.shared_expert_gate",
130
+ "model.layers.5.mlp.shared_expert_gate",
131
+ "model.layers.6.mlp.shared_expert_gate",
132
+ "model.layers.7.mlp.shared_expert_gate",
133
+ "model.layers.8.mlp.shared_expert_gate",
134
+ "model.layers.9.mlp.shared_expert_gate",
135
+ "model.layers.10.mlp.shared_expert_gate",
136
+ "model.layers.11.mlp.shared_expert_gate",
137
+ "model.layers.12.mlp.shared_expert_gate",
138
+ "model.layers.13.mlp.shared_expert_gate",
139
+ "model.layers.14.mlp.shared_expert_gate",
140
+ "model.layers.15.mlp.shared_expert_gate",
141
+ "model.layers.16.mlp.shared_expert_gate",
142
+ "model.layers.17.mlp.shared_expert_gate",
143
+ "model.layers.18.mlp.shared_expert_gate",
144
+ "model.layers.19.mlp.shared_expert_gate",
145
+ "model.layers.20.mlp.shared_expert_gate",
146
+ "model.layers.21.mlp.shared_expert_gate",
147
+ "model.layers.22.mlp.shared_expert_gate",
148
+ "model.layers.23.mlp.shared_expert_gate",
149
+ "model.layers.24.mlp.shared_expert_gate",
150
+ "model.layers.25.mlp.shared_expert_gate",
151
+ "model.layers.26.mlp.shared_expert_gate",
152
+ "model.layers.27.mlp.shared_expert_gate",
153
+ "model.layers.28.mlp.shared_expert_gate",
154
+ "model.layers.29.mlp.shared_expert_gate",
155
+ "model.layers.30.mlp.shared_expert_gate",
156
+ "model.layers.31.mlp.shared_expert_gate",
157
+ "model.layers.32.mlp.shared_expert_gate",
158
+ "model.layers.33.mlp.shared_expert_gate",
159
+ "model.layers.34.mlp.shared_expert_gate",
160
+ "model.layers.35.mlp.shared_expert_gate",
161
+ "model.layers.36.mlp.shared_expert_gate",
162
+ "model.layers.37.mlp.shared_expert_gate",
163
+ "model.layers.38.mlp.shared_expert_gate",
164
+ "model.layers.39.mlp.shared_expert_gate",
165
+ "model.layers.40.mlp.shared_expert_gate",
166
+ "model.layers.41.mlp.shared_expert_gate",
167
+ "model.layers.42.mlp.shared_expert_gate",
168
+ "model.layers.43.mlp.shared_expert_gate",
169
+ "model.layers.44.mlp.shared_expert_gate",
170
+ "model.layers.45.mlp.shared_expert_gate",
171
+ "model.layers.46.mlp.shared_expert_gate",
172
+ "model.layers.47.mlp.shared_expert_gate",
173
+ "lm_head"
174
+ ],
175
+ "kv_cache_scheme": null,
176
+ "quant_method": "compressed-tensors",
177
+ "quantization_status": "compressed",
178
+ "sparsity_config": {},
179
+ "transform_config": {},
180
+ "version": "0.17.0"
181
+ },
182
+ "rms_norm_eps": 1e-06,
183
+ "rope_parameters": {
184
+ "partial_rotary_factor": 0.25,
185
+ "rope_theta": 5000000,
186
+ "rope_type": "default"
187
+ },
188
+ "router_aux_loss_coef": 0.001,
189
+ "shared_expert_intermediate_size": 512,
190
+ "tie_word_embeddings": false,
191
+ "transformers_version": "5.10.1",
192
+ "use_cache": true,
193
+ "use_sliding_window": false,
194
+ "vocab_size": 151936
195
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 1.0,
10
+ "top_k": 40,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.10.1"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b6805337af9cdbc2df0ad002854e0592f172e6adaf44175032113a027ff651
3
+ size 50011183088
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071ef9ead82b85369f44f1f753f7d78318b9015a17dd8a691d22b50d95536690
3
+ size 30508950096
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ff72e7fd1ba30f343849e26164ac0e73f99d64a9e9d69be85eafa169d06eb5
3
+ size 13933421
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*shared_expert_gate.*', 're:.*mlp.gate$', 're:.*router.*']
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:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "local_files_only": false,
25
+ "model_max_length": 1048576,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }