Hugging Face's logo

cyankiwi
/
Qwen3-Coder-Next-REAM-AWQ-4bit

Text Generation
Transformers
Safetensors
qwen3_next
compression
expert-merging
Mixture of Experts
code
conversational
compressed-tensors
Model card Files
xet
 Community
1
cpatonn commited on
Commit
0d4b6f7
·
verified ·
1 Parent(s): 387dace

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +2 -0
  2. README.md +40 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +117 -0
  5. config.json +541 -0
  6. generation_config.json +12 -0
  7. merges.txt +0 -0
  8. model-00001-of-00008.safetensors +3 -0
  9. model-00002-of-00008.safetensors +3 -0
  10. model-00003-of-00008.safetensors +3 -0
  11. model-00004-of-00008.safetensors +3 -0
  12. model-00005-of-00008.safetensors +3 -0
  13. model-00006-of-00008.safetensors +3 -0
  14. model-00007-of-00008.safetensors +3 -0
  15. model-00008-of-00008.safetensors +3 -0
  16. model.safetensors.index.json +3 -0
  17. special_tokens_map.json +31 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +239 -0
  20. vocab.json +0 -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
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - compression
5
+ - expert-merging
6
+ - moe
7
+ - code
8
+ license: apache-2.0
9
+ base_model:
10
+ - bknyaz/Qwen3-Coder-Next-REAM
11
+ ---
12
+
13
+ # Qwen3-Coder-Next-REAM
14
+
15
+ This model is a compressed version of [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next).
16
+ It is obtained by reducing the number of experts in each MoE layer from 512 to 384.
17
+ This reduction is achieved by the REAM method described in https://bknyaz.github.io/blog/2026/moe/.
18
+
19
+ **Compared to other models obtained in this collection, more code data is used in the calibration data during pruning/merging
20
+ to better preserve original's model coding abilities. Specifically, the ratio between c4, math and coding data (see https://bknyaz.github.io/blog/2026/moe/) is 0.0, 0.7, 0.3.
21
+ The calibration data used here is the same as in our [Qwen3-Coder-Next-REAP](https://huggingface.co/SamsungSAILMontreal/Qwen3-Coder-Next-REAP).
22
+ Compared to other REAM models, here we used C=32 (number of experts in groups) instead of C=16, which we found to work better.**
23
+
24
+ The compressed model has 60B params (120GB) instead of 80B (160GB) of the original model,
25
+ reducing storage and GPU memory requirements by roughly 25%. At the same time,
26
+ the model retains 100% (or very close) of the original model's performance on a variety of benchmarks (see Results section below).
27
+ Additional efficiency optimization (e.g., quantization) can be added similarly to the original model.
28
+
29
+ See additional details at [Qwen3-30B-A3B-Instruct-2507-REAM](https://huggingface.co/SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM).
30
+
31
+ ### Results
32
+
33
+ | Model | IFeval | AIME25 | GSM8K | GPQA-D | HumanEval | LiveCodeBench | AVG |
34
+ |--------------------------|--------|--------|-------|--------|-----------|---------------|-------|
35
+ | Qwen3-Coder-Next | 89.6 | 80.0 | 85.4 | 42.4 | 92.7 | 47.5 | 72.9 |
36
+ | Qwen3-Coder-Next-REAM | 89.3 | 80.0 | 85.3 | 40.4 | 94.5 | 48.0 | 72.9 |
37
+
38
+ ## License
39
+
40
+ Please refer to the license of the original model [Qwen/Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next).
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
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 +1,541 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 5120,
17
+ "layer_types": [
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention"
66
+ ],
67
+ "linear_conv_kernel_dim": 4,
68
+ "linear_key_head_dim": 128,
69
+ "linear_num_key_heads": 16,
70
+ "linear_num_value_heads": 32,
71
+ "linear_value_head_dim": 128,
72
+ "max_position_embeddings": 262144,
73
+ "merge_args": {
74
+ "balance_group_size": 32,
75
+ "dataset": "c4+math+the-stack-smol",
76
+ "expert_saliency": "reap",
77
+ "gate_softmax": true,
78
+ "group": "freq_logits",
79
+ "merge": "align_logits_weights",
80
+ "merge_size": 384,
81
+ "merger_bs": 3072,
82
+ "merger_seq_len": 512,
83
+ "pca_dim": 64,
84
+ "precompute_input": false,
85
+ "use_gate_output": true
86
+ },
87
+ "mlp_only_layers": [],
88
+ "model_type": "qwen3_next",
89
+ "moe_intermediate_size": 512,
90
+ "norm_topk_prob": true,
91
+ "num_attention_heads": 16,
92
+ "num_experts": 384,
93
+ "num_experts_per_tok": 10,
94
+ "num_hidden_layers": 48,
95
+ "num_key_value_heads": 2,
96
+ "output_router_logits": false,
97
+ "partial_rotary_factor": 0.25,
98
+ "quantization_config": {
99
+ "config_groups": {
100
+ "group_0": {
101
+ "format": "pack-quantized",
102
+ "input_activations": null,
103
+ "output_activations": null,
104
+ "targets": [
105
+ "Linear"
106
+ ],
107
+ "weights": {
108
+ "actorder": null,
109
+ "block_structure": null,
110
+ "dynamic": false,
111
+ "group_size": 32,
112
+ "num_bits": 4,
113
+ "observer": "mse",
114
+ "observer_kwargs": {},
115
+ "scale_dtype": null,
116
+ "strategy": "group",
117
+ "symmetric": true,
118
+ "type": "int",
119
+ "zp_dtype": null
120
+ }
121
+ }
122
+ },
123
+ "format": "pack-quantized",
124
+ "global_compression_ratio": null,
125
+ "ignore": [
126
+ "model.layers.0.linear_attn.in_proj_qkvz",
127
+ "model.layers.0.linear_attn.in_proj_ba",
128
+ "model.layers.0.linear_attn.out_proj",
129
+ "model.layers.0.mlp.gate",
130
+ "model.layers.0.mlp.shared_expert.gate_proj",
131
+ "model.layers.0.mlp.shared_expert.up_proj",
132
+ "model.layers.0.mlp.shared_expert.down_proj",
133
+ "model.layers.0.mlp.shared_expert_gate",
134
+ "model.layers.1.linear_attn.in_proj_qkvz",
135
+ "model.layers.1.linear_attn.in_proj_ba",
136
+ "model.layers.1.linear_attn.out_proj",
137
+ "model.layers.1.mlp.gate",
138
+ "model.layers.1.mlp.shared_expert.gate_proj",
139
+ "model.layers.1.mlp.shared_expert.up_proj",
140
+ "model.layers.1.mlp.shared_expert.down_proj",
141
+ "model.layers.1.mlp.shared_expert_gate",
142
+ "model.layers.2.linear_attn.in_proj_qkvz",
143
+ "model.layers.2.linear_attn.in_proj_ba",
144
+ "model.layers.2.linear_attn.out_proj",
145
+ "model.layers.2.mlp.gate",
146
+ "model.layers.2.mlp.shared_expert.gate_proj",
147
+ "model.layers.2.mlp.shared_expert.up_proj",
148
+ "model.layers.2.mlp.shared_expert.down_proj",
149
+ "model.layers.2.mlp.shared_expert_gate",
150
+ "model.layers.3.self_attn.q_proj",
151
+ "model.layers.3.self_attn.k_proj",
152
+ "model.layers.3.self_attn.v_proj",
153
+ "model.layers.3.self_attn.o_proj",
154
+ "model.layers.3.mlp.gate",
155
+ "model.layers.3.mlp.shared_expert.gate_proj",
156
+ "model.layers.3.mlp.shared_expert.up_proj",
157
+ "model.layers.3.mlp.shared_expert.down_proj",
158
+ "model.layers.3.mlp.shared_expert_gate",
159
+ "model.layers.4.linear_attn.in_proj_qkvz",
160
+ "model.layers.4.linear_attn.in_proj_ba",
161
+ "model.layers.4.linear_attn.out_proj",
162
+ "model.layers.4.mlp.gate",
163
+ "model.layers.4.mlp.shared_expert.gate_proj",
164
+ "model.layers.4.mlp.shared_expert.up_proj",
165
+ "model.layers.4.mlp.shared_expert.down_proj",
166
+ "model.layers.4.mlp.shared_expert_gate",
167
+ "model.layers.5.linear_attn.in_proj_qkvz",
168
+ "model.layers.5.linear_attn.in_proj_ba",
169
+ "model.layers.5.linear_attn.out_proj",
170
+ "model.layers.5.mlp.gate",
171
+ "model.layers.5.mlp.shared_expert.gate_proj",
172
+ "model.layers.5.mlp.shared_expert.up_proj",
173
+ "model.layers.5.mlp.shared_expert.down_proj",
174
+ "model.layers.5.mlp.shared_expert_gate",
175
+ "model.layers.6.linear_attn.in_proj_qkvz",
176
+ "model.layers.6.linear_attn.in_proj_ba",
177
+ "model.layers.6.linear_attn.out_proj",
178
+ "model.layers.6.mlp.gate",
179
+ "model.layers.6.mlp.shared_expert.gate_proj",
180
+ "model.layers.6.mlp.shared_expert.up_proj",
181
+ "model.layers.6.mlp.shared_expert.down_proj",
182
+ "model.layers.6.mlp.shared_expert_gate",
183
+ "model.layers.7.self_attn.q_proj",
184
+ "model.layers.7.self_attn.k_proj",
185
+ "model.layers.7.self_attn.v_proj",
186
+ "model.layers.7.self_attn.o_proj",
187
+ "model.layers.7.mlp.gate",
188
+ "model.layers.7.mlp.shared_expert.gate_proj",
189
+ "model.layers.7.mlp.shared_expert.up_proj",
190
+ "model.layers.7.mlp.shared_expert.down_proj",
191
+ "model.layers.7.mlp.shared_expert_gate",
192
+ "model.layers.8.linear_attn.in_proj_qkvz",
193
+ "model.layers.8.linear_attn.in_proj_ba",
194
+ "model.layers.8.linear_attn.out_proj",
195
+ "model.layers.8.mlp.gate",
196
+ "model.layers.8.mlp.shared_expert.gate_proj",
197
+ "model.layers.8.mlp.shared_expert.up_proj",
198
+ "model.layers.8.mlp.shared_expert.down_proj",
199
+ "model.layers.8.mlp.shared_expert_gate",
200
+ "model.layers.9.linear_attn.in_proj_qkvz",
201
+ "model.layers.9.linear_attn.in_proj_ba",
202
+ "model.layers.9.linear_attn.out_proj",
203
+ "model.layers.9.mlp.gate",
204
+ "model.layers.9.mlp.shared_expert.gate_proj",
205
+ "model.layers.9.mlp.shared_expert.up_proj",
206
+ "model.layers.9.mlp.shared_expert.down_proj",
207
+ "model.layers.9.mlp.shared_expert_gate",
208
+ "model.layers.10.linear_attn.in_proj_qkvz",
209
+ "model.layers.10.linear_attn.in_proj_ba",
210
+ "model.layers.10.linear_attn.out_proj",
211
+ "model.layers.10.mlp.gate",
212
+ "model.layers.10.mlp.shared_expert.gate_proj",
213
+ "model.layers.10.mlp.shared_expert.up_proj",
214
+ "model.layers.10.mlp.shared_expert.down_proj",
215
+ "model.layers.10.mlp.shared_expert_gate",
216
+ "model.layers.11.self_attn.q_proj",
217
+ "model.layers.11.self_attn.k_proj",
218
+ "model.layers.11.self_attn.v_proj",
219
+ "model.layers.11.self_attn.o_proj",
220
+ "model.layers.11.mlp.gate",
221
+ "model.layers.11.mlp.shared_expert.gate_proj",
222
+ "model.layers.11.mlp.shared_expert.up_proj",
223
+ "model.layers.11.mlp.shared_expert.down_proj",
224
+ "model.layers.11.mlp.shared_expert_gate",
225
+ "model.layers.12.linear_attn.in_proj_qkvz",
226
+ "model.layers.12.linear_attn.in_proj_ba",
227
+ "model.layers.12.linear_attn.out_proj",
228
+ "model.layers.12.mlp.gate",
229
+ "model.layers.12.mlp.shared_expert.gate_proj",
230
+ "model.layers.12.mlp.shared_expert.up_proj",
231
+ "model.layers.12.mlp.shared_expert.down_proj",
232
+ "model.layers.12.mlp.shared_expert_gate",
233
+ "model.layers.13.linear_attn.in_proj_qkvz",
234
+ "model.layers.13.linear_attn.in_proj_ba",
235
+ "model.layers.13.linear_attn.out_proj",
236
+ "model.layers.13.mlp.gate",
237
+ "model.layers.13.mlp.shared_expert.gate_proj",
238
+ "model.layers.13.mlp.shared_expert.up_proj",
239
+ "model.layers.13.mlp.shared_expert.down_proj",
240
+ "model.layers.13.mlp.shared_expert_gate",
241
+ "model.layers.14.linear_attn.in_proj_qkvz",
242
+ "model.layers.14.linear_attn.in_proj_ba",
243
+ "model.layers.14.linear_attn.out_proj",
244
+ "model.layers.14.mlp.gate",
245
+ "model.layers.14.mlp.shared_expert.gate_proj",
246
+ "model.layers.14.mlp.shared_expert.up_proj",
247
+ "model.layers.14.mlp.shared_expert.down_proj",
248
+ "model.layers.14.mlp.shared_expert_gate",
249
+ "model.layers.15.self_attn.q_proj",
250
+ "model.layers.15.self_attn.k_proj",
251
+ "model.layers.15.self_attn.v_proj",
252
+ "model.layers.15.self_attn.o_proj",
253
+ "model.layers.15.mlp.gate",
254
+ "model.layers.15.mlp.shared_expert.gate_proj",
255
+ "model.layers.15.mlp.shared_expert.up_proj",
256
+ "model.layers.15.mlp.shared_expert.down_proj",
257
+ "model.layers.15.mlp.shared_expert_gate",
258
+ "model.layers.16.linear_attn.in_proj_qkvz",
259
+ "model.layers.16.linear_attn.in_proj_ba",
260
+ "model.layers.16.linear_attn.out_proj",
261
+ "model.layers.16.mlp.gate",
262
+ "model.layers.16.mlp.shared_expert.gate_proj",
263
+ "model.layers.16.mlp.shared_expert.up_proj",
264
+ "model.layers.16.mlp.shared_expert.down_proj",
265
+ "model.layers.16.mlp.shared_expert_gate",
266
+ "model.layers.17.linear_attn.in_proj_qkvz",
267
+ "model.layers.17.linear_attn.in_proj_ba",
268
+ "model.layers.17.linear_attn.out_proj",
269
+ "model.layers.17.mlp.gate",
270
+ "model.layers.17.mlp.shared_expert.gate_proj",
271
+ "model.layers.17.mlp.shared_expert.up_proj",
272
+ "model.layers.17.mlp.shared_expert.down_proj",
273
+ "model.layers.17.mlp.shared_expert_gate",
274
+ "model.layers.18.linear_attn.in_proj_qkvz",
275
+ "model.layers.18.linear_attn.in_proj_ba",
276
+ "model.layers.18.linear_attn.out_proj",
277
+ "model.layers.18.mlp.gate",
278
+ "model.layers.18.mlp.shared_expert.gate_proj",
279
+ "model.layers.18.mlp.shared_expert.up_proj",
280
+ "model.layers.18.mlp.shared_expert.down_proj",
281
+ "model.layers.18.mlp.shared_expert_gate",
282
+ "model.layers.19.self_attn.q_proj",
283
+ "model.layers.19.self_attn.k_proj",
284
+ "model.layers.19.self_attn.v_proj",
285
+ "model.layers.19.self_attn.o_proj",
286
+ "model.layers.19.mlp.gate",
287
+ "model.layers.19.mlp.shared_expert.gate_proj",
288
+ "model.layers.19.mlp.shared_expert.up_proj",
289
+ "model.layers.19.mlp.shared_expert.down_proj",
290
+ "model.layers.19.mlp.shared_expert_gate",
291
+ "model.layers.20.linear_attn.in_proj_qkvz",
292
+ "model.layers.20.linear_attn.in_proj_ba",
293
+ "model.layers.20.linear_attn.out_proj",
294
+ "model.layers.20.mlp.gate",
295
+ "model.layers.20.mlp.shared_expert.gate_proj",
296
+ "model.layers.20.mlp.shared_expert.up_proj",
297
+ "model.layers.20.mlp.shared_expert.down_proj",
298
+ "model.layers.20.mlp.shared_expert_gate",
299
+ "model.layers.21.linear_attn.in_proj_qkvz",
300
+ "model.layers.21.linear_attn.in_proj_ba",
301
+ "model.layers.21.linear_attn.out_proj",
302
+ "model.layers.21.mlp.gate",
303
+ "model.layers.21.mlp.shared_expert.gate_proj",
304
+ "model.layers.21.mlp.shared_expert.up_proj",
305
+ "model.layers.21.mlp.shared_expert.down_proj",
306
+ "model.layers.21.mlp.shared_expert_gate",
307
+ "model.layers.22.linear_attn.in_proj_qkvz",
308
+ "model.layers.22.linear_attn.in_proj_ba",
309
+ "model.layers.22.linear_attn.out_proj",
310
+ "model.layers.22.mlp.gate",
311
+ "model.layers.22.mlp.shared_expert.gate_proj",
312
+ "model.layers.22.mlp.shared_expert.up_proj",
313
+ "model.layers.22.mlp.shared_expert.down_proj",
314
+ "model.layers.22.mlp.shared_expert_gate",
315
+ "model.layers.23.self_attn.q_proj",
316
+ "model.layers.23.self_attn.k_proj",
317
+ "model.layers.23.self_attn.v_proj",
318
+ "model.layers.23.self_attn.o_proj",
319
+ "model.layers.23.mlp.gate",
320
+ "model.layers.23.mlp.shared_expert.gate_proj",
321
+ "model.layers.23.mlp.shared_expert.up_proj",
322
+ "model.layers.23.mlp.shared_expert.down_proj",
323
+ "model.layers.23.mlp.shared_expert_gate",
324
+ "model.layers.24.linear_attn.in_proj_qkvz",
325
+ "model.layers.24.linear_attn.in_proj_ba",
326
+ "model.layers.24.linear_attn.out_proj",
327
+ "model.layers.24.mlp.gate",
328
+ "model.layers.24.mlp.shared_expert.gate_proj",
329
+ "model.layers.24.mlp.shared_expert.up_proj",
330
+ "model.layers.24.mlp.shared_expert.down_proj",
331
+ "model.layers.24.mlp.shared_expert_gate",
332
+ "model.layers.25.linear_attn.in_proj_qkvz",
333
+ "model.layers.25.linear_attn.in_proj_ba",
334
+ "model.layers.25.linear_attn.out_proj",
335
+ "model.layers.25.mlp.gate",
336
+ "model.layers.25.mlp.shared_expert.gate_proj",
337
+ "model.layers.25.mlp.shared_expert.up_proj",
338
+ "model.layers.25.mlp.shared_expert.down_proj",
339
+ "model.layers.25.mlp.shared_expert_gate",
340
+ "model.layers.26.linear_attn.in_proj_qkvz",
341
+ "model.layers.26.linear_attn.in_proj_ba",
342
+ "model.layers.26.linear_attn.out_proj",
343
+ "model.layers.26.mlp.gate",
344
+ "model.layers.26.mlp.shared_expert.gate_proj",
345
+ "model.layers.26.mlp.shared_expert.up_proj",
346
+ "model.layers.26.mlp.shared_expert.down_proj",
347
+ "model.layers.26.mlp.shared_expert_gate",
348
+ "model.layers.27.self_attn.q_proj",
349
+ "model.layers.27.self_attn.k_proj",
350
+ "model.layers.27.self_attn.v_proj",
351
+ "model.layers.27.self_attn.o_proj",
352
+ "model.layers.27.mlp.gate",
353
+ "model.layers.27.mlp.shared_expert.gate_proj",
354
+ "model.layers.27.mlp.shared_expert.up_proj",
355
+ "model.layers.27.mlp.shared_expert.down_proj",
356
+ "model.layers.27.mlp.shared_expert_gate",
357
+ "model.layers.28.linear_attn.in_proj_qkvz",
358
+ "model.layers.28.linear_attn.in_proj_ba",
359
+ "model.layers.28.linear_attn.out_proj",
360
+ "model.layers.28.mlp.gate",
361
+ "model.layers.28.mlp.shared_expert.gate_proj",
362
+ "model.layers.28.mlp.shared_expert.up_proj",
363
+ "model.layers.28.mlp.shared_expert.down_proj",
364
+ "model.layers.28.mlp.shared_expert_gate",
365
+ "model.layers.29.linear_attn.in_proj_qkvz",
366
+ "model.layers.29.linear_attn.in_proj_ba",
367
+ "model.layers.29.linear_attn.out_proj",
368
+ "model.layers.29.mlp.gate",
369
+ "model.layers.29.mlp.shared_expert.gate_proj",
370
+ "model.layers.29.mlp.shared_expert.up_proj",
371
+ "model.layers.29.mlp.shared_expert.down_proj",
372
+ "model.layers.29.mlp.shared_expert_gate",
373
+ "model.layers.30.linear_attn.in_proj_qkvz",
374
+ "model.layers.30.linear_attn.in_proj_ba",
375
+ "model.layers.30.linear_attn.out_proj",
376
+ "model.layers.30.mlp.gate",
377
+ "model.layers.30.mlp.shared_expert.gate_proj",
378
+ "model.layers.30.mlp.shared_expert.up_proj",
379
+ "model.layers.30.mlp.shared_expert.down_proj",
380
+ "model.layers.30.mlp.shared_expert_gate",
381
+ "model.layers.31.self_attn.q_proj",
382
+ "model.layers.31.self_attn.k_proj",
383
+ "model.layers.31.self_attn.v_proj",
384
+ "model.layers.31.self_attn.o_proj",
385
+ "model.layers.31.mlp.gate",
386
+ "model.layers.31.mlp.shared_expert.gate_proj",
387
+ "model.layers.31.mlp.shared_expert.up_proj",
388
+ "model.layers.31.mlp.shared_expert.down_proj",
389
+ "model.layers.31.mlp.shared_expert_gate",
390
+ "model.layers.32.linear_attn.in_proj_qkvz",
391
+ "model.layers.32.linear_attn.in_proj_ba",
392
+ "model.layers.32.linear_attn.out_proj",
393
+ "model.layers.32.mlp.gate",
394
+ "model.layers.32.mlp.shared_expert.gate_proj",
395
+ "model.layers.32.mlp.shared_expert.up_proj",
396
+ "model.layers.32.mlp.shared_expert.down_proj",
397
+ "model.layers.32.mlp.shared_expert_gate",
398
+ "model.layers.33.linear_attn.in_proj_qkvz",
399
+ "model.layers.33.linear_attn.in_proj_ba",
400
+ "model.layers.33.linear_attn.out_proj",
401
+ "model.layers.33.mlp.gate",
402
+ "model.layers.33.mlp.shared_expert.gate_proj",
403
+ "model.layers.33.mlp.shared_expert.up_proj",
404
+ "model.layers.33.mlp.shared_expert.down_proj",
405
+ "model.layers.33.mlp.shared_expert_gate",
406
+ "model.layers.34.linear_attn.in_proj_qkvz",
407
+ "model.layers.34.linear_attn.in_proj_ba",
408
+ "model.layers.34.linear_attn.out_proj",
409
+ "model.layers.34.mlp.gate",
410
+ "model.layers.34.mlp.shared_expert.gate_proj",
411
+ "model.layers.34.mlp.shared_expert.up_proj",
412
+ "model.layers.34.mlp.shared_expert.down_proj",
413
+ "model.layers.34.mlp.shared_expert_gate",
414
+ "model.layers.35.self_attn.q_proj",
415
+ "model.layers.35.self_attn.k_proj",
416
+ "model.layers.35.self_attn.v_proj",
417
+ "model.layers.35.self_attn.o_proj",
418
+ "model.layers.35.mlp.gate",
419
+ "model.layers.35.mlp.shared_expert.gate_proj",
420
+ "model.layers.35.mlp.shared_expert.up_proj",
421
+ "model.layers.35.mlp.shared_expert.down_proj",
422
+ "model.layers.35.mlp.shared_expert_gate",
423
+ "model.layers.36.linear_attn.in_proj_qkvz",
424
+ "model.layers.36.linear_attn.in_proj_ba",
425
+ "model.layers.36.linear_attn.out_proj",
426
+ "model.layers.36.mlp.gate",
427
+ "model.layers.36.mlp.shared_expert.gate_proj",
428
+ "model.layers.36.mlp.shared_expert.up_proj",
429
+ "model.layers.36.mlp.shared_expert.down_proj",
430
+ "model.layers.36.mlp.shared_expert_gate",
431
+ "model.layers.37.linear_attn.in_proj_qkvz",
432
+ "model.layers.37.linear_attn.in_proj_ba",
433
+ "model.layers.37.linear_attn.out_proj",
434
+ "model.layers.37.mlp.gate",
435
+ "model.layers.37.mlp.shared_expert.gate_proj",
436
+ "model.layers.37.mlp.shared_expert.up_proj",
437
+ "model.layers.37.mlp.shared_expert.down_proj",
438
+ "model.layers.37.mlp.shared_expert_gate",
439
+ "model.layers.38.linear_attn.in_proj_qkvz",
440
+ "model.layers.38.linear_attn.in_proj_ba",
441
+ "model.layers.38.linear_attn.out_proj",
442
+ "model.layers.38.mlp.gate",
443
+ "model.layers.38.mlp.shared_expert.gate_proj",
444
+ "model.layers.38.mlp.shared_expert.up_proj",
445
+ "model.layers.38.mlp.shared_expert.down_proj",
446
+ "model.layers.38.mlp.shared_expert_gate",
447
+ "model.layers.39.self_attn.q_proj",
448
+ "model.layers.39.self_attn.k_proj",
449
+ "model.layers.39.self_attn.v_proj",
450
+ "model.layers.39.self_attn.o_proj",
451
+ "model.layers.39.mlp.gate",
452
+ "model.layers.39.mlp.shared_expert.gate_proj",
453
+ "model.layers.39.mlp.shared_expert.up_proj",
454
+ "model.layers.39.mlp.shared_expert.down_proj",
455
+ "model.layers.39.mlp.shared_expert_gate",
456
+ "model.layers.40.linear_attn.in_proj_qkvz",
457
+ "model.layers.40.linear_attn.in_proj_ba",
458
+ "model.layers.40.linear_attn.out_proj",
459
+ "model.layers.40.mlp.gate",
460
+ "model.layers.40.mlp.shared_expert.gate_proj",
461
+ "model.layers.40.mlp.shared_expert.up_proj",
462
+ "model.layers.40.mlp.shared_expert.down_proj",
463
+ "model.layers.40.mlp.shared_expert_gate",
464
+ "model.layers.41.linear_attn.in_proj_qkvz",
465
+ "model.layers.41.linear_attn.in_proj_ba",
466
+ "model.layers.41.linear_attn.out_proj",
467
+ "model.layers.41.mlp.gate",
468
+ "model.layers.41.mlp.shared_expert.gate_proj",
469
+ "model.layers.41.mlp.shared_expert.up_proj",
470
+ "model.layers.41.mlp.shared_expert.down_proj",
471
+ "model.layers.41.mlp.shared_expert_gate",
472
+ "model.layers.42.linear_attn.in_proj_qkvz",
473
+ "model.layers.42.linear_attn.in_proj_ba",
474
+ "model.layers.42.linear_attn.out_proj",
475
+ "model.layers.42.mlp.gate",
476
+ "model.layers.42.mlp.shared_expert.gate_proj",
477
+ "model.layers.42.mlp.shared_expert.up_proj",
478
+ "model.layers.42.mlp.shared_expert.down_proj",
479
+ "model.layers.42.mlp.shared_expert_gate",
480
+ "model.layers.43.self_attn.q_proj",
481
+ "model.layers.43.self_attn.k_proj",
482
+ "model.layers.43.self_attn.v_proj",
483
+ "model.layers.43.self_attn.o_proj",
484
+ "model.layers.43.mlp.gate",
485
+ "model.layers.43.mlp.shared_expert.gate_proj",
486
+ "model.layers.43.mlp.shared_expert.up_proj",
487
+ "model.layers.43.mlp.shared_expert.down_proj",
488
+ "model.layers.43.mlp.shared_expert_gate",
489
+ "model.layers.44.linear_attn.in_proj_qkvz",
490
+ "model.layers.44.linear_attn.in_proj_ba",
491
+ "model.layers.44.linear_attn.out_proj",
492
+ "model.layers.44.mlp.gate",
493
+ "model.layers.44.mlp.shared_expert.gate_proj",
494
+ "model.layers.44.mlp.shared_expert.up_proj",
495
+ "model.layers.44.mlp.shared_expert.down_proj",
496
+ "model.layers.44.mlp.shared_expert_gate",
497
+ "model.layers.45.linear_attn.in_proj_qkvz",
498
+ "model.layers.45.linear_attn.in_proj_ba",
499
+ "model.layers.45.linear_attn.out_proj",
500
+ "model.layers.45.mlp.gate",
501
+ "model.layers.45.mlp.shared_expert.gate_proj",
502
+ "model.layers.45.mlp.shared_expert.up_proj",
503
+ "model.layers.45.mlp.shared_expert.down_proj",
504
+ "model.layers.45.mlp.shared_expert_gate",
505
+ "model.layers.46.linear_attn.in_proj_qkvz",
506
+ "model.layers.46.linear_attn.in_proj_ba",
507
+ "model.layers.46.linear_attn.out_proj",
508
+ "model.layers.46.mlp.gate",
509
+ "model.layers.46.mlp.shared_expert.gate_proj",
510
+ "model.layers.46.mlp.shared_expert.up_proj",
511
+ "model.layers.46.mlp.shared_expert.down_proj",
512
+ "model.layers.46.mlp.shared_expert_gate",
513
+ "model.layers.47.self_attn.q_proj",
514
+ "model.layers.47.self_attn.k_proj",
515
+ "model.layers.47.self_attn.v_proj",
516
+ "model.layers.47.self_attn.o_proj",
517
+ "model.layers.47.mlp.gate",
518
+ "model.layers.47.mlp.shared_expert.gate_proj",
519
+ "model.layers.47.mlp.shared_expert.up_proj",
520
+ "model.layers.47.mlp.shared_expert.down_proj",
521
+ "model.layers.47.mlp.shared_expert_gate",
522
+ "lm_head"
523
+ ],
524
+ "kv_cache_scheme": null,
525
+ "quant_method": "compressed-tensors",
526
+ "quantization_status": "compressed",
527
+ "sparsity_config": {},
528
+ "transform_config": {},
529
+ "version": "0.13.1.a20260217"
530
+ },
531
+ "rms_norm_eps": 1e-06,
532
+ "rope_scaling": null,
533
+ "rope_theta": 5000000,
534
+ "router_aux_loss_coef": 0.001,
535
+ "shared_expert_intermediate_size": 512,
536
+ "tie_word_embeddings": false,
537
+ "transformers_version": "4.57.3",
538
+ "use_cache": true,
539
+ "use_sliding_window": false,
540
+ "vocab_size": 151936
541
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "top_k": 40,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.57.6"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1005d7374708358616ba5e701f254d9285c4929dc3cecca8703d8ba7169abdb7
3
+ size 5002322696
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547a0a08a79ba87b5b0df16e0f208a627ad19025f3ab483d6cb27e971acef0d1
3
+ size 5002328784
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe3f81d1bc23e006efd0574f64ed0d8c76868e144a365fcaa3380d304774f32
3
+ size 5002344088
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb5d1b8b0f62a44e33d7b804172cb131a4792ecc0e3f37caf89e4ebf40b4699
3
+ size 5002501288
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071bdff469969452aaf6c7d6b055c5bd5c789e256b0f59d0461ce3d5a3235add
3
+ size 5002343344
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de30fb17ce7b948c288568589a69c4a6b769532b9edf53573a70c1a3bd2ba40
3
+ size 4986353512
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a67fd70403d96b2f32f534f91d41ebe1d27d6c0f94e5ec630279f3a29a9523
3
+ size 5002556056
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04e1db803a271cf8e982a4e063151784cbec9bf586744c18e1a7b12d4490f08
3
+ size 2340450208
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa24c88c5ac7e30e5d4452454bd2975db61c09343be20c767e289e836cd59b81
3
+ size 16176679
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1048576,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff