clonefy commited on
Commit
64ac916
·
verified ·
1 Parent(s): 2e897c0

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +131 -0
  4. config.json +238 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. model-00001-of-00049.safetensors +3 -0
  8. model-00002-of-00049.safetensors +3 -0
  9. model-00003-of-00049.safetensors +3 -0
  10. model-00004-of-00049.safetensors +3 -0
  11. model-00005-of-00049.safetensors +3 -0
  12. model-00006-of-00049.safetensors +3 -0
  13. model-00007-of-00049.safetensors +3 -0
  14. model-00008-of-00049.safetensors +3 -0
  15. model-00009-of-00049.safetensors +3 -0
  16. model-00010-of-00049.safetensors +3 -0
  17. model-00011-of-00049.safetensors +3 -0
  18. model-00012-of-00049.safetensors +3 -0
  19. model-00013-of-00049.safetensors +3 -0
  20. model-00014-of-00049.safetensors +3 -0
  21. model-00015-of-00049.safetensors +3 -0
  22. model-00016-of-00049.safetensors +3 -0
  23. model-00017-of-00049.safetensors +3 -0
  24. model-00018-of-00049.safetensors +3 -0
  25. model-00019-of-00049.safetensors +3 -0
  26. model-00020-of-00049.safetensors +3 -0
  27. model-00021-of-00049.safetensors +3 -0
  28. model-00022-of-00049.safetensors +3 -0
  29. model-00023-of-00049.safetensors +3 -0
  30. model-00024-of-00049.safetensors +3 -0
  31. model-00025-of-00049.safetensors +3 -0
  32. model-00026-of-00049.safetensors +3 -0
  33. model-00027-of-00049.safetensors +3 -0
  34. model-00028-of-00049.safetensors +3 -0
  35. model-00029-of-00049.safetensors +3 -0
  36. model-00030-of-00049.safetensors +3 -0
  37. model-00031-of-00049.safetensors +3 -0
  38. model-00032-of-00049.safetensors +3 -0
  39. model-00033-of-00049.safetensors +3 -0
  40. model-00034-of-00049.safetensors +3 -0
  41. model-00035-of-00049.safetensors +3 -0
  42. model-00036-of-00049.safetensors +3 -0
  43. model-00037-of-00049.safetensors +3 -0
  44. model-00038-of-00049.safetensors +3 -0
  45. model-00039-of-00049.safetensors +3 -0
  46. model-00040-of-00049.safetensors +3 -0
  47. model-00041-of-00049.safetensors +3 -0
  48. model-00042-of-00049.safetensors +3 -0
  49. model-00043-of-00049.safetensors +3 -0
  50. model-00044-of-00049.safetensors +3 -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
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% macro render_item_list(item_list, tag_name='required') %}
2
+ {%- if item_list is defined and item_list is iterable and item_list | length > 0 %}
3
+ {%- if tag_name %}{{- '\n<' ~ tag_name ~ '>' -}}{% endif %}
4
+ {{- '[' }}
5
+ {%- for item in item_list -%}
6
+ {%- if loop.index > 1 %}{{- ", "}}{% endif -%}
7
+ {%- if item is string -%}
8
+ {{ "`" ~ item ~ "`" }}
9
+ {%- else -%}
10
+ {{ item }}
11
+ {%- endif -%}
12
+ {%- endfor -%}
13
+ {{- ']' }}
14
+ {%- if tag_name %}{{- '</' ~ tag_name ~ '>' -}}{% endif %}
15
+ {%- endif %}
16
+ {% endmacro %}
17
+
18
+ {%- if messages[0]["role"] == "system" %}
19
+ {%- set system_message = messages[0]["content"] %}
20
+ {%- set loop_messages = messages[1:] %}
21
+ {%- else %}
22
+ {%- set loop_messages = messages %}
23
+ {%- endif %}
24
+
25
+ {%- if not tools is defined %}
26
+ {%- set tools = [] %}
27
+ {%- endif %}
28
+
29
+ {%- if system_message is defined %}
30
+ {{- "<|im_start|>system\n" + system_message }}
31
+ {%- else %}
32
+ {%- if tools is iterable and tools | length > 0 %}
33
+ {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- if tools is iterable and tools | length > 0 %}
37
+ {{- "\n\nYou have access to the following functions:\n\n" }}
38
+ {{- "<tools>" }}
39
+ {%- for tool in tools %}
40
+ {%- if tool.function is defined %}
41
+ {%- set tool = tool.function %}
42
+ {%- endif %}
43
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
44
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
45
+ {{- '\n<parameters>' }}
46
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
47
+ {{- '\n<parameter>' }}
48
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
49
+ {%- if param_fields.type is defined %}
50
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
51
+ {%- endif %}
52
+ {%- if param_fields.description is defined %}
53
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
54
+ {%- endif %}
55
+ {{- render_item_list(param_fields.enum, 'enum') }}
56
+ {%- set handled_keys = ['type', 'description', 'enum', 'required'] %}
57
+ {%- for json_key in param_fields.keys() | reject("in", handled_keys) %}
58
+ {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}
59
+ {%- if param_fields[json_key] is mapping %}
60
+ {{- '\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | tojson | safe) ~ '</' ~ normed_json_key ~ '>' }}
61
+ {%- else %}
62
+ {{-'\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | string) ~ '</' ~ normed_json_key ~ '>' }}
63
+ {%- endif %}
64
+ {%- endfor %}
65
+ {{- render_item_list(param_fields.required, 'required') }}
66
+ {{- '\n</parameter>' }}
67
+ {%- endfor %}
68
+ {{- render_item_list(tool.parameters.required, 'required') }}
69
+ {{- '\n</parameters>' }}
70
+ {%- if tool.return is defined %}
71
+ {%- if tool.return is mapping %}
72
+ {{- '\n<return>' ~ (tool.return | tojson | safe) ~ '</return>' }}
73
+ {%- else %}
74
+ {{- '\n<return>' ~ (tool.return | string) ~ '</return>' }}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {{- '\n</function>' }}
78
+ {%- endfor %}
79
+ {{- "\n</tools>" }}
80
+ {{- '\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>' }}
81
+ {%- endif %}
82
+ {%- if system_message is defined %}
83
+ {{- '<|im_end|>\n' }}
84
+ {%- else %}
85
+ {%- if tools is iterable and tools | length > 0 %}
86
+ {{- '<|im_end|>\n' }}
87
+ {%- endif %}
88
+ {%- endif %}
89
+ {%- for message in loop_messages %}
90
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
91
+ {{- '<|im_start|>' + message.role }}
92
+ {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
93
+ {{- '\n' + message.content | trim + '\n' }}
94
+ {%- endif %}
95
+ {%- for tool_call in message.tool_calls %}
96
+ {%- if tool_call.function is defined %}
97
+ {%- set tool_call = tool_call.function %}
98
+ {%- endif %}
99
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
100
+ {%- if tool_call.arguments is defined %}
101
+ {%- for args_name, args_value in tool_call.arguments|items %}
102
+ {{- '<parameter=' + args_name + '>\n' }}
103
+ {%- set args_value = args_value if args_value is string else args_value | string %}
104
+ {{- args_value }}
105
+ {{- '\n</parameter>\n' }}
106
+ {%- endfor %}
107
+ {%- endif %}
108
+ {{- '</function>\n</tool_call>' }}
109
+ {%- endfor %}
110
+ {{- '<|im_end|>\n' }}
111
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
112
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
113
+ {%- elif message.role == "tool" %}
114
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
115
+ {{- '<|im_start|>user\n' }}
116
+ {%- endif %}
117
+ {{- '<tool_response>\n' }}
118
+ {{- message.content }}
119
+ {{- '\n</tool_response>\n' }}
120
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
121
+ {{- '<|im_end|>\n' }}
122
+ {%- elif loop.last %}
123
+ {{- '<|im_end|>\n' }}
124
+ {%- endif %}
125
+ {%- else %}
126
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
127
+ {%- endif %}
128
+ {%- endfor %}
129
+ {%- if add_generation_prompt %}
130
+ {{- '<|im_start|>assistant\n' }}
131
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 6144,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 262144,
16
+ "max_window_layers": 28,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 2560,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 96,
22
+ "num_experts": 160,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 62,
25
+ "num_key_value_heads": 8,
26
+ "output_router_logits": false,
27
+ "qkv_bias": false,
28
+ "quantization_config": {
29
+ "activation_scheme": "dynamic",
30
+ "modules_to_not_convert": [
31
+ "lm_head",
32
+ "model.layers.0.input_layernorm",
33
+ "model.layers.0.mlp.gate",
34
+ "model.layers.0.post_attention_layernorm",
35
+ "model.layers.1.input_layernorm",
36
+ "model.layers.1.mlp.gate",
37
+ "model.layers.1.post_attention_layernorm",
38
+ "model.layers.2.input_layernorm",
39
+ "model.layers.2.mlp.gate",
40
+ "model.layers.2.post_attention_layernorm",
41
+ "model.layers.3.input_layernorm",
42
+ "model.layers.3.mlp.gate",
43
+ "model.layers.3.post_attention_layernorm",
44
+ "model.layers.4.input_layernorm",
45
+ "model.layers.4.mlp.gate",
46
+ "model.layers.4.post_attention_layernorm",
47
+ "model.layers.5.input_layernorm",
48
+ "model.layers.5.mlp.gate",
49
+ "model.layers.5.post_attention_layernorm",
50
+ "model.layers.6.input_layernorm",
51
+ "model.layers.6.mlp.gate",
52
+ "model.layers.6.post_attention_layernorm",
53
+ "model.layers.7.input_layernorm",
54
+ "model.layers.7.mlp.gate",
55
+ "model.layers.7.post_attention_layernorm",
56
+ "model.layers.8.input_layernorm",
57
+ "model.layers.8.mlp.gate",
58
+ "model.layers.8.post_attention_layernorm",
59
+ "model.layers.9.input_layernorm",
60
+ "model.layers.9.mlp.gate",
61
+ "model.layers.9.post_attention_layernorm",
62
+ "model.layers.10.input_layernorm",
63
+ "model.layers.10.mlp.gate",
64
+ "model.layers.10.post_attention_layernorm",
65
+ "model.layers.11.input_layernorm",
66
+ "model.layers.11.mlp.gate",
67
+ "model.layers.11.post_attention_layernorm",
68
+ "model.layers.12.input_layernorm",
69
+ "model.layers.12.mlp.gate",
70
+ "model.layers.12.post_attention_layernorm",
71
+ "model.layers.13.input_layernorm",
72
+ "model.layers.13.mlp.gate",
73
+ "model.layers.13.post_attention_layernorm",
74
+ "model.layers.14.input_layernorm",
75
+ "model.layers.14.mlp.gate",
76
+ "model.layers.14.post_attention_layernorm",
77
+ "model.layers.15.input_layernorm",
78
+ "model.layers.15.mlp.gate",
79
+ "model.layers.15.post_attention_layernorm",
80
+ "model.layers.16.input_layernorm",
81
+ "model.layers.16.mlp.gate",
82
+ "model.layers.16.post_attention_layernorm",
83
+ "model.layers.17.input_layernorm",
84
+ "model.layers.17.mlp.gate",
85
+ "model.layers.17.post_attention_layernorm",
86
+ "model.layers.18.input_layernorm",
87
+ "model.layers.18.mlp.gate",
88
+ "model.layers.18.post_attention_layernorm",
89
+ "model.layers.19.input_layernorm",
90
+ "model.layers.19.mlp.gate",
91
+ "model.layers.19.post_attention_layernorm",
92
+ "model.layers.20.input_layernorm",
93
+ "model.layers.20.mlp.gate",
94
+ "model.layers.20.post_attention_layernorm",
95
+ "model.layers.21.input_layernorm",
96
+ "model.layers.21.mlp.gate",
97
+ "model.layers.21.post_attention_layernorm",
98
+ "model.layers.22.input_layernorm",
99
+ "model.layers.22.mlp.gate",
100
+ "model.layers.22.post_attention_layernorm",
101
+ "model.layers.23.input_layernorm",
102
+ "model.layers.23.mlp.gate",
103
+ "model.layers.23.post_attention_layernorm",
104
+ "model.layers.24.input_layernorm",
105
+ "model.layers.24.mlp.gate",
106
+ "model.layers.24.post_attention_layernorm",
107
+ "model.layers.25.input_layernorm",
108
+ "model.layers.25.mlp.gate",
109
+ "model.layers.25.post_attention_layernorm",
110
+ "model.layers.26.input_layernorm",
111
+ "model.layers.26.mlp.gate",
112
+ "model.layers.26.post_attention_layernorm",
113
+ "model.layers.27.input_layernorm",
114
+ "model.layers.27.mlp.gate",
115
+ "model.layers.27.post_attention_layernorm",
116
+ "model.layers.28.input_layernorm",
117
+ "model.layers.28.mlp.gate",
118
+ "model.layers.28.post_attention_layernorm",
119
+ "model.layers.29.input_layernorm",
120
+ "model.layers.29.mlp.gate",
121
+ "model.layers.29.post_attention_layernorm",
122
+ "model.layers.30.input_layernorm",
123
+ "model.layers.30.mlp.gate",
124
+ "model.layers.30.post_attention_layernorm",
125
+ "model.layers.31.input_layernorm",
126
+ "model.layers.31.mlp.gate",
127
+ "model.layers.31.post_attention_layernorm",
128
+ "model.layers.32.input_layernorm",
129
+ "model.layers.32.mlp.gate",
130
+ "model.layers.32.post_attention_layernorm",
131
+ "model.layers.33.input_layernorm",
132
+ "model.layers.33.mlp.gate",
133
+ "model.layers.33.post_attention_layernorm",
134
+ "model.layers.34.input_layernorm",
135
+ "model.layers.34.mlp.gate",
136
+ "model.layers.34.post_attention_layernorm",
137
+ "model.layers.35.input_layernorm",
138
+ "model.layers.35.mlp.gate",
139
+ "model.layers.35.post_attention_layernorm",
140
+ "model.layers.36.input_layernorm",
141
+ "model.layers.36.mlp.gate",
142
+ "model.layers.36.post_attention_layernorm",
143
+ "model.layers.37.input_layernorm",
144
+ "model.layers.37.mlp.gate",
145
+ "model.layers.37.post_attention_layernorm",
146
+ "model.layers.38.input_layernorm",
147
+ "model.layers.38.mlp.gate",
148
+ "model.layers.38.post_attention_layernorm",
149
+ "model.layers.39.input_layernorm",
150
+ "model.layers.39.mlp.gate",
151
+ "model.layers.39.post_attention_layernorm",
152
+ "model.layers.40.input_layernorm",
153
+ "model.layers.40.mlp.gate",
154
+ "model.layers.40.post_attention_layernorm",
155
+ "model.layers.41.input_layernorm",
156
+ "model.layers.41.mlp.gate",
157
+ "model.layers.41.post_attention_layernorm",
158
+ "model.layers.42.input_layernorm",
159
+ "model.layers.42.mlp.gate",
160
+ "model.layers.42.post_attention_layernorm",
161
+ "model.layers.43.input_layernorm",
162
+ "model.layers.43.mlp.gate",
163
+ "model.layers.43.post_attention_layernorm",
164
+ "model.layers.44.input_layernorm",
165
+ "model.layers.44.mlp.gate",
166
+ "model.layers.44.post_attention_layernorm",
167
+ "model.layers.45.input_layernorm",
168
+ "model.layers.45.mlp.gate",
169
+ "model.layers.45.post_attention_layernorm",
170
+ "model.layers.46.input_layernorm",
171
+ "model.layers.46.mlp.gate",
172
+ "model.layers.46.post_attention_layernorm",
173
+ "model.layers.47.input_layernorm",
174
+ "model.layers.47.mlp.gate",
175
+ "model.layers.47.post_attention_layernorm",
176
+ "model.layers.48.input_layernorm",
177
+ "model.layers.48.mlp.gate",
178
+ "model.layers.48.post_attention_layernorm",
179
+ "model.layers.49.input_layernorm",
180
+ "model.layers.49.mlp.gate",
181
+ "model.layers.49.post_attention_layernorm",
182
+ "model.layers.50.input_layernorm",
183
+ "model.layers.50.mlp.gate",
184
+ "model.layers.50.post_attention_layernorm",
185
+ "model.layers.51.input_layernorm",
186
+ "model.layers.51.mlp.gate",
187
+ "model.layers.51.post_attention_layernorm",
188
+ "model.layers.52.input_layernorm",
189
+ "model.layers.52.mlp.gate",
190
+ "model.layers.52.post_attention_layernorm",
191
+ "model.layers.53.input_layernorm",
192
+ "model.layers.53.mlp.gate",
193
+ "model.layers.53.post_attention_layernorm",
194
+ "model.layers.54.input_layernorm",
195
+ "model.layers.54.mlp.gate",
196
+ "model.layers.54.post_attention_layernorm",
197
+ "model.layers.55.input_layernorm",
198
+ "model.layers.55.mlp.gate",
199
+ "model.layers.55.post_attention_layernorm",
200
+ "model.layers.56.input_layernorm",
201
+ "model.layers.56.mlp.gate",
202
+ "model.layers.56.post_attention_layernorm",
203
+ "model.layers.57.input_layernorm",
204
+ "model.layers.57.mlp.gate",
205
+ "model.layers.57.post_attention_layernorm",
206
+ "model.layers.58.input_layernorm",
207
+ "model.layers.58.mlp.gate",
208
+ "model.layers.58.post_attention_layernorm",
209
+ "model.layers.59.input_layernorm",
210
+ "model.layers.59.mlp.gate",
211
+ "model.layers.59.post_attention_layernorm",
212
+ "model.layers.60.input_layernorm",
213
+ "model.layers.60.mlp.gate",
214
+ "model.layers.60.post_attention_layernorm",
215
+ "model.layers.61.input_layernorm",
216
+ "model.layers.61.mlp.gate",
217
+ "model.layers.61.post_attention_layernorm"
218
+ ],
219
+ "quant_method": "fp8",
220
+ "weight_block_size": [
221
+ 128,
222
+ 128
223
+ ]
224
+ },
225
+ "rms_norm_eps": 1e-06,
226
+ "rope_scaling": null,
227
+ "rope_theta": 10000000,
228
+ "router_aux_loss_coef": 0.0,
229
+ "shared_expert_intermediate_size": 0,
230
+ "sliding_window": null,
231
+ "tie_word_embeddings": false,
232
+ "torch_dtype": "bfloat16",
233
+ "transformers_version": "4.52.4",
234
+ "use_cache": true,
235
+ "use_qk_norm": true,
236
+ "use_sliding_window": false,
237
+ "vocab_size": 151936
238
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.52.4"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5e1fb3695be02926ec09f8d46d5fe0499ab5bad792973e20467936c157f965
3
+ size 9984900968
model-00002-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e89f3eeb7bc743905a6fc9bc8a6ef27d7f2b5f47d85d0fcbb8e6ce549971304
3
+ size 9997346816
model-00003-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c86cf377a571560bf36f73c2bab548557d2c5336b014a30d4ace255289b44f
3
+ size 9997346856
model-00004-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e47c1d020c9e3944b735b96fc6877a2f9ee5501306d62dead8a7cc0ab228fa0
3
+ size 9997347136
model-00005-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3da6f32b9fac7215e24be62021f0a9ccd7e0674c9f51f7fb08b1c734823098ae
3
+ size 9989898424
model-00006-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8688e8d26a7ca9e3dbef62a7dae247d85014978d558e91e7bba8d7a611548bc7
3
+ size 9997346848
model-00007-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf602baa71a1e711362e06057dc5b01ce08e11c03bd70596f2fa57b783cf9ba
3
+ size 9997347040
model-00008-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e3583fc9ac98459f995ce00de1e0f20f69e5825c879604fef262dae76f2de8d
3
+ size 9989899528
model-00009-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0054be18235f5a680668868a8b7839da83575148b69ab8de6c671eba1e9671
3
+ size 9997348112
model-00010-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfc85be495ebc6ab7cc2efb2e5e262de478844324537b3cd836d96aec8369e5
3
+ size 9997348184
model-00011-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2c1a5a489db5b7217c69e65ee344ba461c908ead79b0676ce033d9900c4864
3
+ size 9950180760
model-00012-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41897c33c3ffea539e39796f5b606d119ad6e9ec72d80b3dac0c49e4970e69dd
3
+ size 9989874840
model-00013-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05692ebfe61aa8a7d7479f1ee5df8e416a4ae21576074afddaa2d8a545c779c
3
+ size 9997348112
model-00014-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f310ebd39dbc0280c6f920cfb4ed1896aec85b39781b0d8df84f82cf53a166
3
+ size 9997348360
model-00015-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f0a10a49f8db2aa5c08e5a9a15379f9a9bdffeffc40d6576124199ee62e5c8
3
+ size 9989899704
model-00016-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5105a58532352a9802e4fd12d7345f1d467fe866d21fd973abad9d641095e4
3
+ size 9997348112
model-00017-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69954e8e319b404e230c9d76cc9c68ed304d91ee994406e2259993e3e343b22
3
+ size 9997348240
model-00018-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f87ae0f24a92020b0d2ad5c962d1ce4ae9a859bfdac383f2cbd59ef7185059c
3
+ size 9989899840
model-00019-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669d3cfd31b76fcd4556e0afdff75ed512a3c592d88905fadcf0a46ac19a703b
3
+ size 9997348088
model-00020-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6e111d07e3a7b4f796998a08d46900be19c67a8a10f0b2b20acdcc03d98c67
3
+ size 9997348136
model-00021-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9b50185c94eb55fb0aaae147febfebe0fc8e97aeafa437372b3363e8331d56
3
+ size 9997348400
model-00022-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f58ac8051a00a8b4f07a0c6a6f28e714c37715f072bcb2bc2c1f9a8231c20f
3
+ size 9989899664
model-00023-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee024a2cb8ce6a45274960c2a61279de1aad85834a6a3ff207c832d229cabc6f
3
+ size 9997348112
model-00024-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b657832f896619c326270bccd232cfc5d95a7ea328a6bf750559c19dcc62aee
3
+ size 9997348312
model-00025-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b003320079404a5ef55cb253611f8cfc097802e601447848473dc13996571af7
3
+ size 9989899760
model-00026-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86ed89803f3ef7e89b0f81c299026a33d66ce7de1ad15e536fc6edcafe6ef2b
3
+ size 9997348104
model-00027-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce3adf6ead7f0273c6cd74fa77095a5d6074ff828868fc4ceeb20810db1da2b
3
+ size 9997348200
model-00028-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668628f53a82dceaced90396a7919debbf19befbc94efacee5fc65a79047c1f1
3
+ size 9928156904
model-00029-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3566cebf32e22c5e48be0b94605314a49caeb0f6356fe4a2a318387b52b287f
3
+ size 9996167872
model-00030-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1d968c1b5736a96bc80c0e434fd0f3669434f15dc3e183cdbdc208a6e2ad5a
3
+ size 9997348112
model-00031-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f4796d7f92d7cf78b7ea54c009a99fe5b64e2a6368a676ab3cb7d09d34c2ac
3
+ size 9997348368
model-00032-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b728be17d6855173188b5c94866afb39a2ff5cf95c09d10cdec7270d58a5bd8
3
+ size 9989899696
model-00033-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1b10f22d419dfcc4fde4ad34b699015c3b6f4fdc125cf93e340585b5b2d194
3
+ size 9997348112
model-00034-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96649317f0644ac78f561ed0d9dee30a8e7b9f3bea2e37785dadebd679ff1f25
3
+ size 9997348256
model-00035-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e37a3a14349ee4907cba7396144c0637fb10280b10824d88e9b5e3e263de4c9
3
+ size 9989899816
model-00036-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e5b2c17e702d17a11aed1a2123ef3a0fc04536fbe2700df00490b980f27f83
3
+ size 9997348104
model-00037-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640b809ee36dc6c14390623b6e06e694fc803e3aaa0275eb2d5419f5427a2789
3
+ size 9997348144
model-00038-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82a4474c3aef95967ac69178c4179baa7b5f562974c5e6c5a677c4ffecdad88
3
+ size 9997348400
model-00039-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67862f44ff6b1456482a5eaab52b52b848db5fe20eba2298c2994e8b63de421a
3
+ size 9989899656
model-00040-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca78652b591dbdbec2e5a36d2667e33de181507dc6a5c07cf037b3cbdea9b93
3
+ size 9997348112
model-00041-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ceb5403e7debb467bad47d887a070e2776d1cde7ffa8f604c2927f040f3626
3
+ size 9997348320
model-00042-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57df19df663cceeb6ee3e300979c2c58a0f735ed78e838248ea54909e33940f8
3
+ size 9989899744
model-00043-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e2251ad9431ae9d8e234f99dab905a1dd7b2cef10eceba1f07aa4a53aa067f
3
+ size 9997348104
model-00044-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0960a782e34f6731cc7b2f5d84148bbac7f40695d090055c629427c9dad765
3
+ size 9997348216