Hugging Face's logo

zai-org
/
GLM-4.7-FP8

Text Generation
Transformers
Safetensors
English
Chinese
glm4_moe
conversational
compressed-tensors
Model card Files
xet
Community
2
ZHANGYUXUAN-zR commited on
Commit
abb7419
·
verified ·
1 Parent(s): f3e6137

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. chat_template.jinja +86 -0
  2. config.json +922 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00092.safetensors +3 -0
  5. model-00004-of-00092.safetensors +3 -0
  6. model-00005-of-00092.safetensors +3 -0
  7. model-00007-of-00092.safetensors +3 -0
  8. model-00008-of-00092.safetensors +3 -0
  9. model-00009-of-00092.safetensors +3 -0
  10. model-00010-of-00092.safetensors +3 -0
  11. model-00011-of-00092.safetensors +3 -0
  12. model-00012-of-00092.safetensors +3 -0
  13. model-00013-of-00092.safetensors +3 -0
  14. model-00014-of-00092.safetensors +3 -0
  15. model-00015-of-00092.safetensors +3 -0
  16. model-00016-of-00092.safetensors +3 -0
  17. model-00017-of-00092.safetensors +3 -0
  18. model-00018-of-00092.safetensors +3 -0
  19. model-00019-of-00092.safetensors +3 -0
  20. model-00020-of-00092.safetensors +3 -0
  21. model-00021-of-00092.safetensors +3 -0
  22. model-00024-of-00092.safetensors +3 -0
  23. model-00025-of-00092.safetensors +3 -0
  24. model-00026-of-00092.safetensors +3 -0
  25. model-00028-of-00092.safetensors +3 -0
  26. model-00029-of-00092.safetensors +3 -0
  27. model-00030-of-00092.safetensors +3 -0
  28. model-00031-of-00092.safetensors +3 -0
  29. model-00032-of-00092.safetensors +3 -0
  30. model-00033-of-00092.safetensors +3 -0
  31. model-00034-of-00092.safetensors +3 -0
  32. model-00035-of-00092.safetensors +3 -0
  33. model-00036-of-00092.safetensors +3 -0
  34. model-00037-of-00092.safetensors +3 -0
  35. model-00038-of-00092.safetensors +3 -0
  36. model-00039-of-00092.safetensors +3 -0
  37. model-00040-of-00092.safetensors +3 -0
  38. model-00041-of-00092.safetensors +3 -0
  39. model-00042-of-00092.safetensors +3 -0
  40. model-00043-of-00092.safetensors +3 -0
  41. model-00044-of-00092.safetensors +3 -0
  42. model-00045-of-00092.safetensors +3 -0
  43. model-00046-of-00092.safetensors +3 -0
  44. model-00047-of-00092.safetensors +3 -0
  45. model-00048-of-00092.safetensors +3 -0
  46. model-00049-of-00092.safetensors +3 -0
  47. model-00050-of-00092.safetensors +3 -0
  48. model-00051-of-00092.safetensors +3 -0
  49. model.safetensors.index.json +0 -0
  50. tokenizer_config.json +325 -0
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ <|system|>
4
+ # Tools
5
+
6
+ You may call one or more functions to assist with the user query.
7
+
8
+ You are provided with function signatures within <tools></tools> XML tags:
9
+ <tools>
10
+ {% for tool in tools %}
11
+ {{ tool | tojson(ensure_ascii=False) }}
12
+ {% endfor %}
13
+ </tools>
14
+
15
+ For each function call, output the function name and arguments within the following XML format:
16
+ <tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
17
+ {%- macro visible_text(content) -%}
18
+ {%- if content is string -%}
19
+ {{- content }}
20
+ {%- elif content is iterable and content is not mapping -%}
21
+ {%- for item in content -%}
22
+ {%- if item is mapping and item.type == 'text' -%}
23
+ {{- item.text }}
24
+ {%- elif item is string -%}
25
+ {{- item }}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {%- else -%}
29
+ {{- content }}
30
+ {%- endif -%}
31
+ {%- endmacro -%}
32
+ {%- set ns = namespace(last_user_index=-1) %}
33
+ {%- for m in messages %}
34
+ {%- if m.role == 'user' %}
35
+ {% set ns.last_user_index = loop.index0 -%}
36
+ {%- endif %}
37
+ {%- endfor %}
38
+ {% for m in messages %}
39
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
40
+ {%- elif m.role == 'assistant' -%}
41
+ <|assistant|>
42
+ {%- set reasoning_content = '' %}
43
+ {%- set content = visible_text(m.content) %}
44
+ {%- if m.reasoning_content is string %}
45
+ {%- set reasoning_content = m.reasoning_content %}
46
+ {%- else %}
47
+ {%- if '</think>' in content %}
48
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
49
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
53
+ {{ '<think>' + reasoning_content.strip() + '</think>'}}
54
+ {%- else -%}
55
+ {{ '</think>' }}
56
+ {%- endif -%}
57
+ {%- if content.strip() -%}
58
+ {{ content.strip() }}
59
+ {%- endif -%}
60
+ {% if m.tool_calls %}
61
+ {% for tc in m.tool_calls %}
62
+ {%- if tc.function %}
63
+ {%- set tc = tc.function %}
64
+ {%- endif %}
65
+ {{- '<tool_call>' + tc.name -}}
66
+ {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
67
+ {% endif %}
68
+ {%- elif m.role == 'tool' -%}
69
+ {%- if m.content is string -%}
70
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
71
+ {{- '<|observation|>' }}
72
+ {%- endif %}
73
+ {{- '<tool_response>' }}
74
+ {{- m.content }}
75
+ {{- '</tool_response>' }}
76
+ {%- else -%}
77
+ <|observation|>{% for tr in m.content %}
78
+ <tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
79
+ {% endif -%}
80
+ {%- elif m.role == 'system' -%}
81
+ <|system|>{{ visible_text(m.content) }}
82
+ {%- endif -%}
83
+ {%- endfor -%}
84
+ {%- if add_generation_prompt -%}
85
+ <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
86
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4MoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "head_dim": 128,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "intermediate_size": 12288,
11
+ "max_position_embeddings": 202752,
12
+ "model_type": "glm4_moe",
13
+ "moe_intermediate_size": 1536,
14
+ "norm_topk_prob": true,
15
+ "scoring_func": "sigmoid",
16
+ "num_attention_heads": 96,
17
+ "n_group": 1,
18
+ "topk_group": 1,
19
+ "n_routed_experts": 160,
20
+ "n_shared_experts": 1,
21
+ "routed_scaling_factor": 2.5,
22
+ "topk_method": "noaux_tc",
23
+ "moe_router_dtype": "float32",
24
+ "num_experts_per_tok": 8,
25
+ "first_k_dense_replace": 3,
26
+ "use_qk_norm": true,
27
+ "num_hidden_layers": 92,
28
+ "num_key_value_heads": 8,
29
+ "num_nextn_predict_layers": 1,
30
+ "partial_rotary_factor": 0.5,
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": null,
33
+ "rope_theta": 1000000,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "vocab_size": 151552,
37
+ "transformers_version": "4.52.3",
38
+ "eos_token_id": [
39
+ 151329,
40
+ 151336,
41
+ 151338
42
+ ],
43
+ "pad_token_id": 151329,
44
+ "quantization_config": {
45
+ "config_groups": {
46
+ "group_0": {
47
+ "input_activations": {
48
+ "actorder": null,
49
+ "block_structure": null,
50
+ "dynamic": true,
51
+ "group_size": null,
52
+ "num_bits": 8,
53
+ "observer": null,
54
+ "observer_kwargs": {},
55
+ "strategy": "token",
56
+ "symmetric": true,
57
+ "type": "float"
58
+ },
59
+ "output_activations": null,
60
+ "targets": [
61
+ "Linear"
62
+ ],
63
+ "weights": {
64
+ "actorder": null,
65
+ "block_structure": null,
66
+ "dynamic": false,
67
+ "group_size": null,
68
+ "num_bits": 8,
69
+ "observer": "minmax",
70
+ "observer_kwargs": {},
71
+ "strategy": "channel",
72
+ "symmetric": true,
73
+ "type": "float"
74
+ }
75
+ }
76
+ },
77
+ "format": "float-quantized",
78
+ "ignore": [
79
+ "model.layers.46.post_attention_layernorm",
80
+ "model.layers.16.mlp.gate",
81
+ "model.layers.36.self_attn.k_proj.bias",
82
+ "model.layers.88.self_attn.k_norm",
83
+ "model.layers.17.self_attn.q_proj.bias",
84
+ "model.layers.26.self_attn.v_proj.bias",
85
+ "model.layers.5.mlp.gate",
86
+ "model.layers.59.input_layernorm",
87
+ "model.layers.24.self_attn.k_proj.bias",
88
+ "model.layers.40.self_attn.v_proj.bias",
89
+ "model.layers.55.mlp.gate.e_score_correction_bias",
90
+ "model.layers.72.self_attn.v_proj.bias",
91
+ "model.layers.62.self_attn.q_norm",
92
+ "model.layers.24.self_attn.q_norm",
93
+ "model.layers.7.self_attn.q_norm",
94
+ "model.layers.78.self_attn.k_proj.bias",
95
+ "model.layers.75.self_attn.q_norm",
96
+ "model.layers.45.post_attention_layernorm",
97
+ "model.layers.50.self_attn.k_norm",
98
+ "model.layers.22.self_attn.v_proj.bias",
99
+ "model.layers.15.post_attention_layernorm",
100
+ "model.layers.24.input_layernorm",
101
+ "model.layers.24.mlp.gate.e_score_correction_bias",
102
+ "model.layers.34.self_attn.q_norm",
103
+ "model.layers.21.post_attention_layernorm",
104
+ "model.layers.15.self_attn.k_norm",
105
+ "model.layers.82.self_attn.v_proj.bias",
106
+ "model.layers.60.self_attn.q_proj.bias",
107
+ "model.layers.86.self_attn.k_norm",
108
+ "model.layers.91.input_layernorm",
109
+ "model.layers.67.self_attn.q_proj.bias",
110
+ "model.layers.27.self_attn.k_norm",
111
+ "model.layers.76.self_attn.q_proj.bias",
112
+ "model.layers.53.self_attn.v_proj.bias",
113
+ "model.layers.8.self_attn.k_proj.bias",
114
+ "model.layers.81.self_attn.k_proj.bias",
115
+ "model.layers.20.self_attn.k_norm",
116
+ "model.layers.24.self_attn.v_proj.bias",
117
+ "model.layers.81.input_layernorm",
118
+ "model.layers.23.mlp.gate",
119
+ "model.layers.42.input_layernorm",
120
+ "model.layers.48.mlp.gate.e_score_correction_bias",
121
+ "model.layers.91.self_attn.q_proj.bias",
122
+ "model.layers.32.self_attn.q_norm",
123
+ "model.layers.23.input_layernorm",
124
+ "model.layers.49.mlp.gate",
125
+ "model.layers.54.self_attn.v_proj.bias",
126
+ "model.layers.62.self_attn.k_proj.bias",
127
+ "model.layers.90.self_attn.k_norm",
128
+ "model.layers.72.self_attn.k_proj.bias",
129
+ "model.layers.39.self_attn.q_norm",
130
+ "model.layers.28.self_attn.v_proj.bias",
131
+ "model.layers.63.self_attn.k_proj.bias",
132
+ "model.layers.17.self_attn.v_proj.bias",
133
+ "model.layers.72.post_attention_layernorm",
134
+ "model.layers.26.input_layernorm",
135
+ "model.layers.77.mlp.gate.e_score_correction_bias",
136
+ "model.layers.33.mlp.gate.e_score_correction_bias",
137
+ "model.layers.54.self_attn.k_proj.bias",
138
+ "model.layers.72.self_attn.k_norm",
139
+ "model.layers.87.self_attn.k_proj.bias",
140
+ "model.layers.22.input_layernorm",
141
+ "model.layers.90.mlp.gate",
142
+ "model.layers.38.self_attn.k_proj.bias",
143
+ "model.layers.20.input_layernorm",
144
+ "model.layers.4.self_attn.k_proj.bias",
145
+ "model.layers.43.mlp.gate",
146
+ "model.layers.37.post_attention_layernorm",
147
+ "model.layers.14.mlp.gate",
148
+ "model.layers.79.post_attention_layernorm",
149
+ "model.layers.84.self_attn.k_norm",
150
+ "model.layers.71.self_attn.q_norm",
151
+ "model.layers.56.mlp.gate.e_score_correction_bias",
152
+ "model.layers.6.self_attn.k_proj.bias",
153
+ "model.layers.70.self_attn.k_proj.bias",
154
+ "model.layers.54.post_attention_layernorm",
155
+ "model.layers.55.self_attn.q_norm",
156
+ "model.layers.4.mlp.gate",
157
+ "model.layers.81.mlp.gate",
158
+ "model.layers.7.mlp.gate",
159
+ "model.layers.8.self_attn.q_norm",
160
+ "model.layers.57.self_attn.v_proj.bias",
161
+ "model.layers.65.self_attn.q_norm",
162
+ "model.layers.88.post_attention_layernorm",
163
+ "model.layers.19.input_layernorm",
164
+ "model.layers.6.self_attn.v_proj.bias",
165
+ "model.layers.4.input_layernorm",
166
+ "model.layers.71.self_attn.k_norm",
167
+ "model.layers.32.self_attn.k_norm",
168
+ "model.layers.22.post_attention_layernorm",
169
+ "model.layers.6.self_attn.q_proj.bias",
170
+ "model.layers.61.self_attn.q_norm",
171
+ "model.layers.3.input_layernorm",
172
+ "model.layers.13.input_layernorm",
173
+ "model.layers.74.self_attn.k_norm",
174
+ "model.layers.59.self_attn.v_proj.bias",
175
+ "model.layers.60.self_attn.v_proj.bias",
176
+ "model.layers.35.self_attn.q_proj.bias",
177
+ "model.layers.18.post_attention_layernorm",
178
+ "model.layers.44.self_attn.k_proj.bias",
179
+ "model.layers.64.mlp.gate",
180
+ "model.layers.61.post_attention_layernorm",
181
+ "model.layers.46.self_attn.k_norm",
182
+ "model.layers.19.post_attention_layernorm",
183
+ "model.layers.66.input_layernorm",
184
+ "model.layers.40.mlp.gate.e_score_correction_bias",
185
+ "model.layers.18.self_attn.k_norm",
186
+ "model.layers.30.input_layernorm",
187
+ "model.layers.56.self_attn.v_proj.bias",
188
+ "model.layers.49.self_attn.v_proj.bias",
189
+ "model.layers.3.self_attn.v_proj.bias",
190
+ "model.layers.72.mlp.gate.e_score_correction_bias",
191
+ "model.layers.79.self_attn.k_norm",
192
+ "model.layers.92.self_attn.k_norm",
193
+ "model.layers.79.self_attn.v_proj.bias",
194
+ "model.layers.32.mlp.gate.e_score_correction_bias",
195
+ "model.layers.26.mlp.gate.e_score_correction_bias",
196
+ "model.embed_tokens",
197
+ "model.layers.18.mlp.gate",
198
+ "model.layers.62.self_attn.q_proj.bias",
199
+ "model.layers.44.post_attention_layernorm",
200
+ "model.layers.55.post_attention_layernorm",
201
+ "model.layers.18.input_layernorm",
202
+ "model.layers.46.mlp.gate.e_score_correction_bias",
203
+ "model.layers.75.mlp.gate",
204
+ "model.layers.63.self_attn.q_norm",
205
+ "model.layers.36.mlp.gate.e_score_correction_bias",
206
+ "model.layers.66.self_attn.q_norm",
207
+ "model.layers.45.mlp.gate",
208
+ "model.layers.24.post_attention_layernorm",
209
+ "model.layers.45.self_attn.k_norm",
210
+ "model.layers.0.self_attn.q_proj.bias",
211
+ "model.layers.42.mlp.gate.e_score_correction_bias",
212
+ "model.layers.64.self_attn.q_norm",
213
+ "model.layers.8.input_layernorm",
214
+ "model.layers.26.self_attn.q_proj.bias",
215
+ "model.layers.32.post_attention_layernorm",
216
+ "model.layers.40.self_attn.k_norm",
217
+ "model.layers.91.self_attn.q_norm",
218
+ "model.layers.69.post_attention_layernorm",
219
+ "model.layers.27.self_attn.v_proj.bias",
220
+ "model.layers.9.self_attn.k_norm",
221
+ "model.layers.62.self_attn.k_norm",
222
+ "model.layers.92.input_layernorm",
223
+ "model.layers.14.self_attn.q_proj.bias",
224
+ "model.layers.84.input_layernorm",
225
+ "model.layers.88.mlp.gate",
226
+ "model.layers.7.self_attn.v_proj.bias",
227
+ "model.layers.14.self_attn.q_norm",
228
+ "model.layers.17.self_attn.q_norm",
229
+ "model.layers.85.mlp.gate",
230
+ "model.layers.63.mlp.gate",
231
+ "model.layers.66.self_attn.q_proj.bias",
232
+ "model.layers.76.self_attn.k_proj.bias",
233
+ "model.layers.18.self_attn.q_norm",
234
+ "model.layers.77.post_attention_layernorm",
235
+ "model.layers.55.self_attn.k_norm",
236
+ "model.layers.37.self_attn.q_norm",
237
+ "model.layers.91.post_attention_layernorm",
238
+ "model.layers.53.self_attn.q_norm",
239
+ "model.layers.76.input_layernorm",
240
+ "model.layers.1.self_attn.v_proj.bias",
241
+ "model.layers.38.self_attn.v_proj.bias",
242
+ "model.layers.14.mlp.gate.e_score_correction_bias",
243
+ "model.layers.9.self_attn.v_proj.bias",
244
+ "model.layers.75.post_attention_layernorm",
245
+ "model.layers.9.self_attn.q_norm",
246
+ "model.layers.57.mlp.gate.e_score_correction_bias",
247
+ "model.layers.82.self_attn.k_norm",
248
+ "model.layers.7.post_attention_layernorm",
249
+ "model.layers.43.self_attn.q_norm",
250
+ "model.layers.91.self_attn.k_proj.bias",
251
+ "model.layers.29.self_attn.k_norm",
252
+ "model.layers.11.self_attn.k_proj.bias",
253
+ "model.layers.6.mlp.gate",
254
+ "model.layers.7.self_attn.q_proj.bias",
255
+ "model.layers.63.post_attention_layernorm",
256
+ "model.layers.11.self_attn.q_proj.bias",
257
+ "model.layers.25.input_layernorm",
258
+ "model.layers.21.input_layernorm",
259
+ "model.layers.61.input_layernorm",
260
+ "model.layers.37.mlp.gate.e_score_correction_bias",
261
+ "model.layers.65.mlp.gate",
262
+ "model.layers.20.self_attn.q_norm",
263
+ "model.layers.60.post_attention_layernorm",
264
+ "model.layers.35.self_attn.k_proj.bias",
265
+ "model.layers.70.mlp.gate.e_score_correction_bias",
266
+ "model.layers.85.self_attn.k_norm",
267
+ "model.layers.58.input_layernorm",
268
+ "model.layers.66.self_attn.v_proj.bias",
269
+ "model.layers.80.self_attn.q_norm",
270
+ "model.layers.59.self_attn.k_norm",
271
+ "model.layers.47.self_attn.k_proj.bias",
272
+ "model.layers.46.mlp.gate",
273
+ "model.layers.27.self_attn.k_proj.bias",
274
+ "model.layers.71.self_attn.k_proj.bias",
275
+ "model.layers.76.self_attn.q_norm",
276
+ "model.layers.16.input_layernorm",
277
+ "model.layers.56.self_attn.k_proj.bias",
278
+ "model.layers.30.self_attn.q_proj.bias",
279
+ "model.layers.89.self_attn.q_norm",
280
+ "model.layers.80.self_attn.k_norm",
281
+ "model.layers.40.mlp.gate",
282
+ "model.layers.10.mlp.gate.e_score_correction_bias",
283
+ "model.layers.89.self_attn.k_proj.bias",
284
+ "model.layers.41.mlp.gate.e_score_correction_bias",
285
+ "model.layers.79.self_attn.q_norm",
286
+ "model.layers.49.self_attn.k_proj.bias",
287
+ "model.layers.43.self_attn.k_norm",
288
+ "model.layers.21.self_attn.q_proj.bias",
289
+ "model.layers.69.self_attn.v_proj.bias",
290
+ "model.layers.70.self_attn.k_norm",
291
+ "model.layers.65.self_attn.k_norm",
292
+ "model.layers.59.mlp.gate.e_score_correction_bias",
293
+ "model.layers.92.post_attention_layernorm",
294
+ "model.layers.81.self_attn.v_proj.bias",
295
+ "model.layers.51.input_layernorm",
296
+ "model.layers.3.post_attention_layernorm",
297
+ "model.layers.28.post_attention_layernorm",
298
+ "model.layers.1.self_attn.q_proj.bias",
299
+ "model.layers.0.self_attn.v_proj.bias",
300
+ "model.layers.10.self_attn.q_norm",
301
+ "model.layers.34.mlp.gate.e_score_correction_bias",
302
+ "model.layers.52.self_attn.v_proj.bias",
303
+ "model.layers.1.self_attn.q_norm",
304
+ "model.layers.89.self_attn.k_norm",
305
+ "model.layers.27.mlp.gate.e_score_correction_bias",
306
+ "model.layers.53.self_attn.k_norm",
307
+ "model.layers.61.self_attn.v_proj.bias",
308
+ "model.layers.78.input_layernorm",
309
+ "model.layers.2.self_attn.v_proj.bias",
310
+ "model.layers.76.post_attention_layernorm",
311
+ "model.layers.36.self_attn.q_norm",
312
+ "model.layers.68.self_attn.q_proj.bias",
313
+ "model.layers.33.self_attn.k_proj.bias",
314
+ "model.layers.78.mlp.gate",
315
+ "model.layers.36.mlp.gate",
316
+ "model.layers.44.mlp.gate",
317
+ "model.layers.54.mlp.gate.e_score_correction_bias",
318
+ "model.layers.73.mlp.gate.e_score_correction_bias",
319
+ "model.layers.41.self_attn.k_proj.bias",
320
+ "model.layers.63.self_attn.k_norm",
321
+ "model.layers.29.self_attn.q_proj.bias",
322
+ "model.layers.22.self_attn.q_norm",
323
+ "model.layers.74.self_attn.q_proj.bias",
324
+ "model.layers.47.post_attention_layernorm",
325
+ "model.layers.64.input_layernorm",
326
+ "model.layers.77.self_attn.k_norm",
327
+ "model.layers.27.mlp.gate",
328
+ "model.layers.33.self_attn.q_proj.bias",
329
+ "model.layers.77.self_attn.v_proj.bias",
330
+ "model.layers.87.input_layernorm",
331
+ "model.layers.5.input_layernorm",
332
+ "model.layers.14.self_attn.k_proj.bias",
333
+ "model.layers.32.input_layernorm",
334
+ "model.layers.35.input_layernorm",
335
+ "model.layers.44.self_attn.q_norm",
336
+ "model.layers.51.self_attn.k_norm",
337
+ "model.layers.80.self_attn.v_proj.bias",
338
+ "model.layers.63.self_attn.v_proj.bias",
339
+ "model.layers.4.self_attn.k_norm",
340
+ "model.layers.89.self_attn.q_proj.bias",
341
+ "model.layers.61.self_attn.q_proj.bias",
342
+ "model.layers.9.post_attention_layernorm",
343
+ "model.layers.29.self_attn.v_proj.bias",
344
+ "model.layers.92.hnorm",
345
+ "model.layers.53.self_attn.q_proj.bias",
346
+ "model.layers.73.self_attn.k_norm",
347
+ "model.layers.91.mlp.gate.e_score_correction_bias",
348
+ "model.layers.75.self_attn.q_proj.bias",
349
+ "model.layers.47.self_attn.q_norm",
350
+ "model.layers.77.mlp.gate",
351
+ "model.layers.21.mlp.gate.e_score_correction_bias",
352
+ "model.layers.90.self_attn.v_proj.bias",
353
+ "model.layers.44.mlp.gate.e_score_correction_bias",
354
+ "model.layers.37.self_attn.k_proj.bias",
355
+ "model.layers.92.mlp.gate",
356
+ "model.layers.32.mlp.gate",
357
+ "model.layers.54.input_layernorm",
358
+ "model.layers.13.self_attn.q_proj.bias",
359
+ "model.layers.0.post_attention_layernorm",
360
+ "model.layers.84.mlp.gate.e_score_correction_bias",
361
+ "model.layers.31.mlp.gate.e_score_correction_bias",
362
+ "model.layers.57.self_attn.q_norm",
363
+ "model.layers.83.post_attention_layernorm",
364
+ "model.layers.61.mlp.gate.e_score_correction_bias",
365
+ "model.layers.49.input_layernorm",
366
+ "model.layers.50.mlp.gate.e_score_correction_bias",
367
+ "model.layers.48.self_attn.k_norm",
368
+ "model.layers.18.self_attn.v_proj.bias",
369
+ "model.layers.54.self_attn.q_proj.bias",
370
+ "model.layers.8.mlp.gate.e_score_correction_bias",
371
+ "model.layers.14.self_attn.v_proj.bias",
372
+ "model.layers.5.self_attn.q_norm",
373
+ "model.layers.90.mlp.gate.e_score_correction_bias",
374
+ "model.layers.83.mlp.gate.e_score_correction_bias",
375
+ "model.layers.69.input_layernorm",
376
+ "model.layers.82.self_attn.k_proj.bias",
377
+ "model.layers.86.self_attn.q_norm",
378
+ "model.layers.65.input_layernorm",
379
+ "model.layers.16.mlp.gate.e_score_correction_bias",
380
+ "model.layers.22.mlp.gate.e_score_correction_bias",
381
+ "model.layers.80.mlp.gate.e_score_correction_bias",
382
+ "model.layers.8.self_attn.q_proj.bias",
383
+ "model.layers.23.self_attn.q_norm",
384
+ "model.layers.11.self_attn.k_norm",
385
+ "model.layers.53.mlp.gate.e_score_correction_bias",
386
+ "model.layers.65.self_attn.v_proj.bias",
387
+ "model.layers.47.mlp.gate",
388
+ "model.layers.70.mlp.gate",
389
+ "model.layers.12.mlp.gate.e_score_correction_bias",
390
+ "model.layers.38.mlp.gate.e_score_correction_bias",
391
+ "model.layers.46.self_attn.k_proj.bias",
392
+ "model.layers.64.self_attn.k_norm",
393
+ "model.layers.89.mlp.gate",
394
+ "model.layers.44.self_attn.v_proj.bias",
395
+ "model.layers.33.self_attn.k_norm",
396
+ "model.layers.8.self_attn.k_norm",
397
+ "model.layers.1.self_attn.k_proj.bias",
398
+ "model.layers.51.self_attn.q_proj.bias",
399
+ "lm_head",
400
+ "model.layers.42.self_attn.k_norm",
401
+ "model.layers.60.input_layernorm",
402
+ "model.layers.59.self_attn.q_proj.bias",
403
+ "model.layers.52.self_attn.q_norm",
404
+ "model.layers.84.self_attn.q_proj.bias",
405
+ "model.layers.51.mlp.gate",
406
+ "model.layers.81.self_attn.k_norm",
407
+ "model.layers.1.input_layernorm",
408
+ "model.layers.33.self_attn.q_norm",
409
+ "model.layers.78.mlp.gate.e_score_correction_bias",
410
+ "model.layers.17.post_attention_layernorm",
411
+ "model.layers.50.self_attn.k_proj.bias",
412
+ "model.layers.73.input_layernorm",
413
+ "model.layers.16.self_attn.q_proj.bias",
414
+ "model.layers.70.self_attn.q_proj.bias",
415
+ "model.layers.26.post_attention_layernorm",
416
+ "model.layers.27.input_layernorm",
417
+ "model.layers.86.self_attn.q_proj.bias",
418
+ "model.layers.33.self_attn.v_proj.bias",
419
+ "model.layers.50.mlp.gate",
420
+ "model.layers.64.post_attention_layernorm",
421
+ "model.layers.73.self_attn.q_proj.bias",
422
+ "model.layers.72.input_layernorm",
423
+ "model.layers.66.self_attn.k_norm",
424
+ "model.layers.50.self_attn.v_proj.bias",
425
+ "model.layers.24.self_attn.k_norm",
426
+ "model.layers.69.self_attn.k_norm",
427
+ "model.layers.75.self_attn.k_norm",
428
+ "model.layers.36.input_layernorm",
429
+ "model.layers.40.self_attn.q_norm",
430
+ "model.layers.33.input_layernorm",
431
+ "model.layers.92.enorm",
432
+ "model.layers.23.self_attn.k_norm",
433
+ "model.layers.25.mlp.gate.e_score_correction_bias",
434
+ "model.layers.74.self_attn.q_norm",
435
+ "model.layers.13.self_attn.q_norm",
436
+ "model.layers.75.self_attn.v_proj.bias",
437
+ "model.layers.30.self_attn.v_proj.bias",
438
+ "model.layers.42.self_attn.v_proj.bias",
439
+ "model.layers.29.input_layernorm",
440
+ "model.layers.91.self_attn.k_norm",
441
+ "model.layers.92.self_attn.k_proj.bias",
442
+ "model.layers.12.self_attn.v_proj.bias",
443
+ "model.layers.19.self_attn.v_proj.bias",
444
+ "model.layers.70.self_attn.q_norm",
445
+ "model.layers.75.self_attn.k_proj.bias",
446
+ "model.layers.49.post_attention_layernorm",
447
+ "model.layers.50.self_attn.q_proj.bias",
448
+ "model.layers.84.post_attention_layernorm",
449
+ "model.layers.7.mlp.gate.e_score_correction_bias",
450
+ "model.layers.59.post_attention_layernorm",
451
+ "model.layers.86.input_layernorm",
452
+ "model.layers.22.self_attn.k_proj.bias",
453
+ "model.layers.31.self_attn.q_proj.bias",
454
+ "model.layers.30.post_attention_layernorm",
455
+ "model.layers.79.input_layernorm",
456
+ "model.layers.3.self_attn.k_proj.bias",
457
+ "model.layers.66.self_attn.k_proj.bias",
458
+ "model.layers.81.mlp.gate.e_score_correction_bias",
459
+ "model.layers.88.mlp.gate.e_score_correction_bias",
460
+ "model.layers.29.self_attn.k_proj.bias",
461
+ "model.layers.4.self_attn.q_proj.bias",
462
+ "model.layers.79.self_attn.q_proj.bias",
463
+ "model.layers.35.post_attention_layernorm",
464
+ "model.layers.63.input_layernorm",
465
+ "model.layers.12.self_attn.q_proj.bias",
466
+ "model.layers.0.self_attn.q_norm",
467
+ "model.layers.13.post_attention_layernorm",
468
+ "model.layers.58.self_attn.q_proj.bias",
469
+ "model.layers.90.self_attn.k_proj.bias",
470
+ "model.layers.45.self_attn.v_proj.bias",
471
+ "model.layers.86.self_attn.k_proj.bias",
472
+ "model.layers.38.input_layernorm",
473
+ "model.layers.70.post_attention_layernorm",
474
+ "model.layers.69.self_attn.k_proj.bias",
475
+ "model.layers.88.input_layernorm",
476
+ "model.layers.75.input_layernorm",
477
+ "model.layers.76.mlp.gate.e_score_correction_bias",
478
+ "model.layers.76.mlp.gate",
479
+ "model.layers.8.post_attention_layernorm",
480
+ "model.layers.30.mlp.gate",
481
+ "model.layers.38.self_attn.q_proj.bias",
482
+ "model.layers.19.self_attn.q_norm",
483
+ "model.layers.76.self_attn.k_norm",
484
+ "model.layers.79.mlp.gate",
485
+ "model.layers.23.self_attn.v_proj.bias",
486
+ "model.layers.27.self_attn.q_proj.bias",
487
+ "model.layers.57.post_attention_layernorm",
488
+ "model.layers.56.mlp.gate",
489
+ "model.layers.45.mlp.gate.e_score_correction_bias",
490
+ "model.layers.76.self_attn.v_proj.bias",
491
+ "model.layers.26.self_attn.q_norm",
492
+ "model.layers.17.self_attn.k_norm",
493
+ "model.layers.19.mlp.gate.e_score_correction_bias",
494
+ "model.layers.6.post_attention_layernorm",
495
+ "model.layers.12.post_attention_layernorm",
496
+ "model.layers.71.input_layernorm",
497
+ "model.layers.5.post_attention_layernorm",
498
+ "model.layers.25.self_attn.k_norm",
499
+ "model.layers.37.mlp.gate",
500
+ "model.layers.20.self_attn.k_proj.bias",
501
+ "model.layers.20.self_attn.v_proj.bias",
502
+ "model.layers.52.input_layernorm",
503
+ "model.layers.43.post_attention_layernorm",
504
+ "model.layers.51.post_attention_layernorm",
505
+ "model.layers.12.mlp.gate",
506
+ "model.layers.47.input_layernorm",
507
+ "model.layers.49.self_attn.q_norm",
508
+ "model.layers.78.self_attn.q_proj.bias",
509
+ "model.layers.53.input_layernorm",
510
+ "model.layers.11.mlp.gate",
511
+ "model.layers.88.self_attn.q_norm",
512
+ "model.layers.36.self_attn.q_proj.bias",
513
+ "model.layers.58.self_attn.q_norm",
514
+ "model.layers.77.input_layernorm",
515
+ "model.layers.41.post_attention_layernorm",
516
+ "model.layers.74.self_attn.v_proj.bias",
517
+ "model.layers.2.self_attn.q_norm",
518
+ "model.layers.5.self_attn.k_proj.bias",
519
+ "model.layers.92.self_attn.v_proj.bias",
520
+ "model.layers.58.self_attn.k_norm",
521
+ "model.layers.5.mlp.gate.e_score_correction_bias",
522
+ "model.layers.71.mlp.gate.e_score_correction_bias",
523
+ "model.layers.87.mlp.gate.e_score_correction_bias",
524
+ "model.layers.46.input_layernorm",
525
+ "model.layers.66.mlp.gate.e_score_correction_bias",
526
+ "model.layers.74.post_attention_layernorm",
527
+ "model.layers.80.self_attn.k_proj.bias",
528
+ "model.layers.25.self_attn.v_proj.bias",
529
+ "model.layers.14.self_attn.k_norm",
530
+ "model.layers.3.mlp.gate.e_score_correction_bias",
531
+ "model.layers.57.self_attn.q_proj.bias",
532
+ "model.layers.19.self_attn.q_proj.bias",
533
+ "model.layers.68.mlp.gate",
534
+ "model.layers.28.input_layernorm",
535
+ "model.layers.41.self_attn.q_norm",
536
+ "model.layers.4.mlp.gate.e_score_correction_bias",
537
+ "model.layers.37.input_layernorm",
538
+ "model.layers.91.mlp.gate",
539
+ "model.layers.35.mlp.gate.e_score_correction_bias",
540
+ "model.layers.39.mlp.gate",
541
+ "model.layers.30.self_attn.q_norm",
542
+ "model.layers.87.post_attention_layernorm",
543
+ "model.layers.52.self_attn.k_proj.bias",
544
+ "model.layers.11.self_attn.q_norm",
545
+ "model.layers.59.self_attn.k_proj.bias",
546
+ "model.layers.86.mlp.gate.e_score_correction_bias",
547
+ "model.layers.85.post_attention_layernorm",
548
+ "model.layers.83.mlp.gate",
549
+ "model.layers.70.input_layernorm",
550
+ "model.layers.69.self_attn.q_proj.bias",
551
+ "model.layers.92.eh_proj",
552
+ "model.layers.83.self_attn.k_norm",
553
+ "model.layers.85.self_attn.v_proj.bias",
554
+ "model.layers.34.input_layernorm",
555
+ "model.layers.70.self_attn.v_proj.bias",
556
+ "model.layers.34.self_attn.k_norm",
557
+ "model.layers.67.mlp.gate",
558
+ "model.layers.85.mlp.gate.e_score_correction_bias",
559
+ "model.layers.11.self_attn.v_proj.bias",
560
+ "model.layers.21.mlp.gate",
561
+ "model.layers.0.self_attn.k_proj.bias",
562
+ "model.layers.20.mlp.gate.e_score_correction_bias",
563
+ "model.layers.55.self_attn.k_proj.bias",
564
+ "model.layers.73.self_attn.k_proj.bias",
565
+ "model.layers.29.self_attn.q_norm",
566
+ "model.layers.41.self_attn.k_norm",
567
+ "model.layers.65.post_attention_layernorm",
568
+ "model.layers.46.self_attn.q_proj.bias",
569
+ "model.layers.83.self_attn.v_proj.bias",
570
+ "model.layers.73.self_attn.v_proj.bias",
571
+ "model.layers.82.post_attention_layernorm",
572
+ "model.layers.11.mlp.gate.e_score_correction_bias",
573
+ "model.layers.87.mlp.gate",
574
+ "model.layers.36.self_attn.v_proj.bias",
575
+ "model.layers.40.self_attn.k_proj.bias",
576
+ "model.layers.17.self_attn.k_proj.bias",
577
+ "model.layers.60.mlp.gate.e_score_correction_bias",
578
+ "model.layers.39.post_attention_layernorm",
579
+ "model.layers.61.self_attn.k_proj.bias",
580
+ "model.layers.91.self_attn.v_proj.bias",
581
+ "model.layers.49.mlp.gate.e_score_correction_bias",
582
+ "model.layers.19.self_attn.k_proj.bias",
583
+ "model.layers.32.self_attn.v_proj.bias",
584
+ "model.layers.77.self_attn.q_proj.bias",
585
+ "model.layers.33.post_attention_layernorm",
586
+ "model.layers.68.self_attn.k_norm",
587
+ "model.layers.73.self_attn.q_norm",
588
+ "model.layers.37.self_attn.v_proj.bias",
589
+ "model.layers.86.self_attn.v_proj.bias",
590
+ "model.layers.52.self_attn.k_norm",
591
+ "model.layers.6.self_attn.q_norm",
592
+ "model.layers.86.post_attention_layernorm",
593
+ "model.layers.47.self_attn.v_proj.bias",
594
+ "model.layers.15.self_attn.k_proj.bias",
595
+ "model.layers.21.self_attn.k_norm",
596
+ "model.layers.48.post_attention_layernorm",
597
+ "model.layers.82.mlp.gate",
598
+ "model.layers.88.self_attn.v_proj.bias",
599
+ "model.layers.85.self_attn.k_proj.bias",
600
+ "model.layers.74.mlp.gate.e_score_correction_bias",
601
+ "model.layers.43.mlp.gate.e_score_correction_bias",
602
+ "model.layers.74.mlp.gate",
603
+ "model.layers.84.self_attn.k_proj.bias",
604
+ "model.layers.29.post_attention_layernorm",
605
+ "model.layers.38.self_attn.k_norm",
606
+ "model.layers.7.self_attn.k_norm",
607
+ "model.layers.28.self_attn.k_proj.bias",
608
+ "model.layers.25.post_attention_layernorm",
609
+ "model.layers.35.self_attn.q_norm",
610
+ "model.layers.34.mlp.gate",
611
+ "model.layers.25.mlp.gate",
612
+ "model.layers.31.mlp.gate",
613
+ "model.layers.55.mlp.gate",
614
+ "model.layers.49.self_attn.q_proj.bias",
615
+ "model.layers.83.self_attn.q_proj.bias",
616
+ "model.layers.88.self_attn.k_proj.bias",
617
+ "model.layers.50.input_layernorm",
618
+ "model.layers.67.input_layernorm",
619
+ "model.layers.78.post_attention_layernorm",
620
+ "model.layers.13.mlp.gate.e_score_correction_bias",
621
+ "model.layers.60.self_attn.k_norm",
622
+ "model.layers.15.self_attn.q_norm",
623
+ "model.layers.72.mlp.gate",
624
+ "model.layers.1.self_attn.k_norm",
625
+ "model.layers.92.self_attn.q_norm",
626
+ "model.layers.20.post_attention_layernorm",
627
+ "model.layers.42.self_attn.k_proj.bias",
628
+ "model.layers.80.mlp.gate",
629
+ "model.layers.29.mlp.gate.e_score_correction_bias",
630
+ "model.layers.4.self_attn.q_norm",
631
+ "model.layers.60.self_attn.q_norm",
632
+ "model.layers.52.post_attention_layernorm",
633
+ "model.layers.48.self_attn.k_proj.bias",
634
+ "model.layers.37.self_attn.q_proj.bias",
635
+ "model.layers.65.self_attn.q_proj.bias",
636
+ "model.layers.31.post_attention_layernorm",
637
+ "model.layers.4.self_attn.v_proj.bias",
638
+ "model.layers.28.self_attn.k_norm",
639
+ "model.layers.38.self_attn.q_norm",
640
+ "model.layers.3.mlp.gate",
641
+ "model.layers.89.mlp.gate.e_score_correction_bias",
642
+ "model.layers.81.self_attn.q_proj.bias",
643
+ "model.layers.15.mlp.gate",
644
+ "model.layers.55.self_attn.v_proj.bias",
645
+ "model.layers.69.self_attn.q_norm",
646
+ "model.layers.77.self_attn.q_norm",
647
+ "model.layers.5.self_attn.k_norm",
648
+ "model.layers.9.input_layernorm",
649
+ "model.layers.62.mlp.gate.e_score_correction_bias",
650
+ "model.layers.23.post_attention_layernorm",
651
+ "model.layers.83.self_attn.k_proj.bias",
652
+ "model.layers.34.self_attn.q_proj.bias",
653
+ "model.layers.82.mlp.gate.e_score_correction_bias",
654
+ "model.layers.89.self_attn.v_proj.bias",
655
+ "model.layers.10.post_attention_layernorm",
656
+ "model.layers.42.self_attn.q_proj.bias",
657
+ "model.layers.2.input_layernorm",
658
+ "model.layers.66.mlp.gate",
659
+ "model.layers.87.self_attn.q_proj.bias",
660
+ "model.layers.46.self_attn.v_proj.bias",
661
+ "model.layers.17.mlp.gate.e_score_correction_bias",
662
+ "model.layers.16.self_attn.k_proj.bias",
663
+ "model.layers.2.post_attention_layernorm",
664
+ "model.layers.2.self_attn.k_norm",
665
+ "model.layers.90.self_attn.q_norm",
666
+ "model.layers.42.self_attn.q_norm",
667
+ "model.layers.37.self_attn.k_norm",
668
+ "model.layers.54.self_attn.k_norm",
669
+ "model.layers.68.input_layernorm",
670
+ "model.layers.3.self_attn.k_norm",
671
+ "model.layers.31.self_attn.k_proj.bias",
672
+ "model.layers.79.self_attn.k_proj.bias",
673
+ "model.layers.33.mlp.gate",
674
+ "model.layers.87.self_attn.q_norm",
675
+ "model.layers.68.post_attention_layernorm",
676
+ "model.layers.87.self_attn.k_norm",
677
+ "model.layers.0.self_attn.k_norm",
678
+ "model.layers.4.post_attention_layernorm",
679
+ "model.layers.26.self_attn.k_proj.bias",
680
+ "model.layers.39.self_attn.q_proj.bias",
681
+ "model.layers.71.mlp.gate",
682
+ "model.layers.43.self_attn.k_proj.bias",
683
+ "model.layers.50.post_attention_layernorm",
684
+ "model.layers.41.self_attn.v_proj.bias",
685
+ "model.layers.9.mlp.gate",
686
+ "model.layers.89.input_layernorm",
687
+ "model.layers.73.mlp.gate",
688
+ "model.layers.7.self_attn.k_proj.bias",
689
+ "model.layers.10.self_attn.v_proj.bias",
690
+ "model.layers.3.self_attn.q_norm",
691
+ "model.layers.12.self_attn.k_norm",
692
+ "model.layers.40.input_layernorm",
693
+ "model.layers.21.self_attn.v_proj.bias",
694
+ "model.layers.22.self_attn.k_norm",
695
+ "model.layers.16.post_attention_layernorm",
696
+ "model.layers.81.post_attention_layernorm",
697
+ "model.layers.56.self_attn.q_norm",
698
+ "model.layers.10.self_attn.k_norm",
699
+ "model.layers.35.mlp.gate",
700
+ "model.layers.65.self_attn.k_proj.bias",
701
+ "model.layers.41.input_layernorm",
702
+ "model.layers.80.input_layernorm",
703
+ "model.layers.31.input_layernorm",
704
+ "model.layers.30.self_attn.k_proj.bias",
705
+ "model.layers.49.self_attn.k_norm",
706
+ "model.layers.56.self_attn.k_norm",
707
+ "model.layers.92.embed_tokens",
708
+ "model.layers.42.mlp.gate",
709
+ "model.layers.84.self_attn.q_norm",
710
+ "model.layers.13.self_attn.v_proj.bias",
711
+ "model.layers.21.self_attn.k_proj.bias",
712
+ "model.layers.50.self_attn.q_norm",
713
+ "model.layers.44.self_attn.k_norm",
714
+ "model.layers.10.self_attn.k_proj.bias",
715
+ "model.layers.80.post_attention_layernorm",
716
+ "model.layers.12.input_layernorm",
717
+ "model.layers.57.self_attn.k_proj.bias",
718
+ "model.layers.27.post_attention_layernorm",
719
+ "model.layers.73.post_attention_layernorm",
720
+ "model.layers.90.input_layernorm",
721
+ "model.layers.68.self_attn.v_proj.bias",
722
+ "model.layers.19.mlp.gate",
723
+ "model.layers.9.self_attn.k_proj.bias",
724
+ "model.layers.54.mlp.gate",
725
+ "model.layers.78.self_attn.k_norm",
726
+ "model.layers.32.self_attn.q_proj.bias",
727
+ "model.layers.15.self_attn.q_proj.bias",
728
+ "model.layers.25.self_attn.q_norm",
729
+ "model.layers.23.self_attn.k_proj.bias",
730
+ "model.layers.57.self_attn.k_norm",
731
+ "model.layers.12.self_attn.q_norm",
732
+ "model.layers.56.self_attn.q_proj.bias",
733
+ "model.layers.48.input_layernorm",
734
+ "model.layers.44.self_attn.q_proj.bias",
735
+ "model.layers.45.self_attn.q_norm",
736
+ "model.layers.83.self_attn.q_norm",
737
+ "model.layers.39.self_attn.k_proj.bias",
738
+ "model.layers.40.self_attn.q_proj.bias",
739
+ "model.layers.84.self_attn.v_proj.bias",
740
+ "model.layers.48.mlp.gate",
741
+ "model.layers.15.mlp.gate.e_score_correction_bias",
742
+ "model.layers.67.self_attn.k_proj.bias",
743
+ "model.layers.62.mlp.gate",
744
+ "model.layers.28.mlp.gate.e_score_correction_bias",
745
+ "model.layers.18.self_attn.q_proj.bias",
746
+ "model.layers.9.self_attn.q_proj.bias",
747
+ "model.layers.26.self_attn.k_norm",
748
+ "model.layers.65.mlp.gate.e_score_correction_bias",
749
+ "model.layers.22.mlp.gate",
750
+ "model.layers.68.self_attn.k_proj.bias",
751
+ "model.layers.32.self_attn.k_proj.bias",
752
+ "model.layers.56.post_attention_layernorm",
753
+ "model.layers.54.self_attn.q_norm",
754
+ "model.layers.59.self_attn.q_norm",
755
+ "model.layers.71.post_attention_layernorm",
756
+ "model.layers.1.post_attention_layernorm",
757
+ "model.layers.64.self_attn.q_proj.bias",
758
+ "model.layers.68.mlp.gate.e_score_correction_bias",
759
+ "model.layers.41.mlp.gate",
760
+ "model.layers.22.self_attn.q_proj.bias",
761
+ "model.layers.31.self_attn.v_proj.bias",
762
+ "model.layers.74.input_layernorm",
763
+ "model.layers.27.self_attn.q_norm",
764
+ "model.layers.34.self_attn.v_proj.bias",
765
+ "model.layers.45.input_layernorm",
766
+ "model.layers.39.self_attn.v_proj.bias",
767
+ "model.layers.16.self_attn.k_norm",
768
+ "model.layers.62.input_layernorm",
769
+ "model.layers.24.self_attn.q_proj.bias",
770
+ "model.layers.17.input_layernorm",
771
+ "model.layers.17.mlp.gate",
772
+ "model.layers.29.mlp.gate",
773
+ "model.layers.51.self_attn.v_proj.bias",
774
+ "model.layers.14.post_attention_layernorm",
775
+ "model.layers.13.self_attn.k_norm",
776
+ "model.layers.43.self_attn.v_proj.bias",
777
+ "model.layers.56.input_layernorm",
778
+ "model.layers.77.self_attn.k_proj.bias",
779
+ "model.layers.79.mlp.gate.e_score_correction_bias",
780
+ "model.layers.82.input_layernorm",
781
+ "model.layers.26.mlp.gate",
782
+ "model.layers.78.self_attn.v_proj.bias",
783
+ "model.layers.5.self_attn.q_proj.bias",
784
+ "model.layers.39.mlp.gate.e_score_correction_bias",
785
+ "model.layers.67.self_attn.v_proj.bias",
786
+ "model.layers.51.self_attn.k_proj.bias",
787
+ "model.layers.35.self_attn.v_proj.bias",
788
+ "model.layers.67.self_attn.k_norm",
789
+ "model.layers.69.mlp.gate.e_score_correction_bias",
790
+ "model.layers.39.input_layernorm",
791
+ "model.layers.86.mlp.gate",
792
+ "model.layers.88.self_attn.q_proj.bias",
793
+ "model.layers.2.self_attn.k_proj.bias",
794
+ "model.layers.23.mlp.gate.e_score_correction_bias",
795
+ "model.layers.18.self_attn.k_proj.bias",
796
+ "model.layers.38.mlp.gate",
797
+ "model.layers.59.mlp.gate",
798
+ "model.layers.58.mlp.gate",
799
+ "model.layers.25.self_attn.q_proj.bias",
800
+ "model.layers.72.self_attn.q_proj.bias",
801
+ "model.layers.64.self_attn.k_proj.bias",
802
+ "model.layers.71.self_attn.v_proj.bias",
803
+ "model.layers.92.shared_head.norm",
804
+ "model.layers.43.input_layernorm",
805
+ "model.layers.30.self_attn.k_norm",
806
+ "model.layers.53.mlp.gate",
807
+ "model.layers.7.input_layernorm",
808
+ "model.layers.62.self_attn.v_proj.bias",
809
+ "model.layers.47.self_attn.k_norm",
810
+ "model.layers.53.post_attention_layernorm",
811
+ "model.layers.60.mlp.gate",
812
+ "model.layers.85.self_attn.q_proj.bias",
813
+ "model.layers.53.self_attn.k_proj.bias",
814
+ "model.layers.48.self_attn.q_proj.bias",
815
+ "model.layers.15.self_attn.v_proj.bias",
816
+ "model.layers.71.self_attn.q_proj.bias",
817
+ "model.layers.84.mlp.gate",
818
+ "model.layers.20.self_attn.q_proj.bias",
819
+ "model.layers.8.self_attn.v_proj.bias",
820
+ "model.layers.20.mlp.gate",
821
+ "model.layers.39.self_attn.k_norm",
822
+ "model.layers.57.mlp.gate",
823
+ "model.layers.40.post_attention_layernorm",
824
+ "model.layers.62.post_attention_layernorm",
825
+ "model.layers.68.self_attn.q_norm",
826
+ "model.layers.8.mlp.gate",
827
+ "model.layers.55.self_attn.q_proj.bias",
828
+ "model.layers.52.mlp.gate.e_score_correction_bias",
829
+ "model.layers.60.self_attn.k_proj.bias",
830
+ "model.layers.47.self_attn.q_proj.bias",
831
+ "model.layers.0.input_layernorm",
832
+ "model.layers.12.self_attn.k_proj.bias",
833
+ "model.layers.21.self_attn.q_norm",
834
+ "model.layers.51.self_attn.q_norm",
835
+ "model.layers.80.self_attn.q_proj.bias",
836
+ "model.layers.15.input_layernorm",
837
+ "model.layers.18.mlp.gate.e_score_correction_bias",
838
+ "model.layers.2.self_attn.q_proj.bias",
839
+ "model.layers.58.self_attn.k_proj.bias",
840
+ "model.layers.58.post_attention_layernorm",
841
+ "model.layers.5.self_attn.v_proj.bias",
842
+ "model.layers.3.self_attn.q_proj.bias",
843
+ "model.layers.75.mlp.gate.e_score_correction_bias",
844
+ "model.layers.45.self_attn.q_proj.bias",
845
+ "model.layers.43.self_attn.q_proj.bias",
846
+ "model.layers.28.self_attn.q_proj.bias",
847
+ "model.layers.10.mlp.gate",
848
+ "model.layers.36.post_attention_layernorm",
849
+ "model.layers.19.self_attn.k_norm",
850
+ "model.layers.66.post_attention_layernorm",
851
+ "model.layers.90.post_attention_layernorm",
852
+ "model.layers.23.self_attn.q_proj.bias",
853
+ "model.layers.87.self_attn.v_proj.bias",
854
+ "model.layers.36.self_attn.k_norm",
855
+ "model.layers.35.self_attn.k_norm",
856
+ "model.layers.44.input_layernorm",
857
+ "model.layers.24.mlp.gate",
858
+ "model.layers.34.post_attention_layernorm",
859
+ "model.layers.11.post_attention_layernorm",
860
+ "model.layers.13.mlp.gate",
861
+ "model.layers.85.input_layernorm",
862
+ "model.layers.52.mlp.gate",
863
+ "model.norm",
864
+ "model.layers.51.mlp.gate.e_score_correction_bias",
865
+ "model.layers.25.self_attn.k_proj.bias",
866
+ "model.layers.64.self_attn.v_proj.bias",
867
+ "model.layers.45.self_attn.k_proj.bias",
868
+ "model.layers.82.self_attn.q_proj.bias",
869
+ "model.layers.30.mlp.gate.e_score_correction_bias",
870
+ "model.layers.31.self_attn.k_norm",
871
+ "model.layers.67.mlp.gate.e_score_correction_bias",
872
+ "model.layers.52.self_attn.q_proj.bias",
873
+ "model.layers.57.input_layernorm",
874
+ "model.layers.69.mlp.gate",
875
+ "model.layers.85.self_attn.q_norm",
876
+ "model.layers.78.self_attn.q_norm",
877
+ "model.layers.10.self_attn.q_proj.bias",
878
+ "model.layers.48.self_attn.q_norm",
879
+ "model.layers.92.mlp.gate.e_score_correction_bias",
880
+ "model.layers.67.post_attention_layernorm",
881
+ "model.layers.28.self_attn.q_norm",
882
+ "model.layers.74.self_attn.k_proj.bias",
883
+ "model.layers.58.mlp.gate.e_score_correction_bias",
884
+ "model.layers.67.self_attn.q_norm",
885
+ "model.layers.46.self_attn.q_norm",
886
+ "model.layers.82.self_attn.q_norm",
887
+ "model.layers.9.mlp.gate.e_score_correction_bias",
888
+ "model.layers.16.self_attn.q_norm",
889
+ "model.layers.92.self_attn.q_proj.bias",
890
+ "model.layers.63.mlp.gate.e_score_correction_bias",
891
+ "model.layers.38.post_attention_layernorm",
892
+ "model.layers.72.self_attn.q_norm",
893
+ "model.layers.81.self_attn.q_norm",
894
+ "model.layers.63.self_attn.q_proj.bias",
895
+ "model.layers.48.self_attn.v_proj.bias",
896
+ "model.layers.6.input_layernorm",
897
+ "model.layers.61.mlp.gate",
898
+ "model.layers.14.input_layernorm",
899
+ "model.layers.31.self_attn.q_norm",
900
+ "model.layers.61.self_attn.k_norm",
901
+ "model.layers.83.input_layernorm",
902
+ "model.layers.89.post_attention_layernorm",
903
+ "model.layers.28.mlp.gate",
904
+ "model.layers.16.self_attn.v_proj.bias",
905
+ "model.layers.10.input_layernorm",
906
+ "model.layers.6.mlp.gate.e_score_correction_bias",
907
+ "model.layers.6.self_attn.k_norm",
908
+ "model.layers.11.input_layernorm",
909
+ "model.layers.34.self_attn.k_proj.bias",
910
+ "model.layers.41.self_attn.q_proj.bias",
911
+ "model.layers.58.self_attn.v_proj.bias",
912
+ "model.layers.90.self_attn.q_proj.bias",
913
+ "model.layers.55.input_layernorm",
914
+ "model.layers.13.self_attn.k_proj.bias",
915
+ "model.layers.64.mlp.gate.e_score_correction_bias",
916
+ "model.layers.47.mlp.gate.e_score_correction_bias",
917
+ "model.layers.42.post_attention_layernorm"
918
+ ],
919
+ "quant_method": "compressed-tensors",
920
+ "quantization_status": "compressed"
921
+ }
922
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151329,
5
+ 151336,
6
+ 151338
7
+ ],
8
+ "pad_token_id": 151329,
9
+ "transformers_version": "5.0.0.rc1"
10
+ }
model-00001-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24ac19970bc8cdf2c5b354d207f4383338efe0ac1c8001d3a0ea9c87400d30d
3
+ size 1877199832
model-00004-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab06a236f9e27dbb744c9d375beccec008b87d8abbf481b67fb102987636de1
3
+ size 3941945016
model-00005-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3e1da720ba691d5942816d3419ec27523a44e76f64d1934b9478224463066f
3
+ size 3941945016
model-00007-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f341621619f4e35c18f81f84c372b20b4c2e7bb80ea73a084d7cb1ebbe43a0db
3
+ size 3941945016
model-00008-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b035e2726b8962cfac5d22326887d8f006a42e92248334b504edbaa30b85995
3
+ size 3941945016
model-00009-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13892f0d9a1d494b07d8bc1a20218aa1bfa86a5b39722cae77c599566f3a65a9
3
+ size 3941945016
model-00010-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10700a305f025ce24c75cc1ada5f777cb139a53b7455a2b6ca7c3b2056cf15f5
3
+ size 3941945016
model-00011-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713b14aebf4f359c547348102c9337cd4b593c2a55a9eae524bd294a7df491c2
3
+ size 3941946000
model-00012-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378c5f41081c5ecbebbdd2d32c2e914d39a5c2fac207746658cf038501d7201c
3
+ size 3941946000
model-00013-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ac9caa486b86b9f739ee2077a1ad45a006b1de2b1b00df1d284f5e4883a7da
3
+ size 3941946000
model-00014-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2f33827d6a3b82b7f23a9f549f1df2c8d96d78f1b8f9693675f5f62c8bfd43
3
+ size 3941946000
model-00015-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aa6d38c7cdf78e3805bff96f7322f444fbaca2e72105f47101b2c2e2fa8b7a
3
+ size 3941946000
model-00016-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62bf2d44d7a726ad8a7362fef138a7aa531b6cb548162f23c9a048d1202f242
3
+ size 3941946000
model-00017-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a61323217ccc2bb9be793bed4919c983163e7da805700d746dc28b3211ca9f9
3
+ size 3941946000
model-00018-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cde01d1c9e0a5c0ff8b77ddfa63ca0f4cb1a591a1d2e289b8ad41baf315da2c
3
+ size 3941946000
model-00019-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4785cf1c063fdbfd2a3d2106151d0669ef2bf31c5e40e85546347c153a4debe4
3
+ size 3941946000
model-00020-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d454b5f40cb25a8b58b9d17f59d36d246e400395787820bea6688d25dc7c80b
3
+ size 3941946000
model-00021-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc9a4f5f08dcbc447d625c0c34ed1096bb4be258657fd1af466ae6072249c27
3
+ size 3941946000
model-00024-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7731b4fc4b99d24615995459892f899dcaeb027239c6da5a771ba3ce7e274b9f
3
+ size 3941946000
model-00025-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9019ff499bc60270a464f98328137b2c666523ecefc1eb06ac7c323442d319a
3
+ size 3941946000
model-00026-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcf1249e96e0978d389bda6890ea2e35de2b974140646530165964eba230c29
3
+ size 3941946000
model-00028-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097cd090f5dae2d7094fc02d5c1af624852508a8395840b47b47d12e5d1d6c53
3
+ size 3941946000
model-00029-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914f4bc7787a85abd89033cff0ccd61fce0c25711f3736601d4d7c8ac36e1fe7
3
+ size 3941946000
model-00030-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48821212171025cb83f25ec615b76f1f3c5004b58059876a0e80ff3d88a6fc23
3
+ size 3941946000
model-00031-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab80ef7aae34dd71722ba5b7c72e734990c7237a164df7b94dba2ca1268a63f0
3
+ size 3941946000
model-00032-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59bc55addd93bc05211c14da6ca84caf280ede8f1d14756fdb984954eacf78f6
3
+ size 3941946000
model-00033-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e42eca2b6fbd071e4b57c214208741c8de58eb06b272f3af1172bd46be3c03
3
+ size 3941946000
model-00034-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78533da697011fa78c6ce64e16cb1047fa6ddae2dce942b98b02507bf9a2f04c
3
+ size 3941946000
model-00035-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77aaa1413ba2ec147a28c21be42cdcf85214cf7d3c253751a13ec5ccf371ad8e
3
+ size 3941946000
model-00036-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9365c279beacc4b74bff190d26f70d66a78834754439fc69cf2d5c6278d85a23
3
+ size 3941946000
model-00037-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b986433974e12880cd94133bba326f6d2dfd839bc6334dd9825f4915cc56534
3
+ size 3941946000
model-00038-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a40fb8a043fae9a24940f89d238b2dc0bd796c1b075ea72148d61e0248e84e
3
+ size 3941946000
model-00039-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5897cea06087af1a46f28f94b8262aba1e9ba7bc04fe464ba77b6909614658a1
3
+ size 3941946000
model-00040-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06174320d7812248be593d5f1f644cca59c2903a37278af45d34ccafe0570713
3
+ size 3941946000
model-00041-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833e4f5881a41c1e9e68a57fab2003f2ef6e918fe9e11359c68379c5d14bd7b4
3
+ size 3941946000
model-00042-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9625b9a4fa1eabbd32f5a928176f32e1ae6ef9a764aacbe09aab1e694daa0c
3
+ size 3941946000
model-00043-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f11c5bdc5841dd9a3cc32414d1c7053876ab4aeb79ae4b1981be69a39cb872
3
+ size 3941946000
model-00044-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25b5174cd0fb13060dd7a5c4a85fe449e2369462098461b9b5f55efec363888
3
+ size 3941946000
model-00045-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5968f108ab9d680eaf2152ad807120abdde7e8a759bfcfe1f3e1b4554374df
3
+ size 3941946000
model-00046-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fab04915d4fc87fe836f3a0136fd539b2c41e99043aeea42e4b6aac2fbea463
3
+ size 3941946000
model-00047-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7a0eb76704a9faa568cccf62852eedab31618077fda57895ace4ede918dd12
3
+ size 3941946000
model-00048-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9485d72fe534020a4edd45fdcbfb8ab79fa620b03e84f9ea0ffc21081f3aaf3c
3
+ size 3941946000
model-00049-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7706f122286598a73ca8a189f6b83d96abcb970040aa79e3413d5b26362ebdec
3
+ size 3941946000
model-00050-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82dd581fcbe94b373bc10a27cdf0813c970c74937825243d2793088186e2826
3
+ size 3941946000
model-00051-of-00092.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16eefe1ccd26e632945c23efcfcbd1d7a79f45011445944eaf45851fc78f88d
3
+ size 3941946000
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|begin_of_audio|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|end_of_audio|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "151346": {
140
+ "content": "<|end_of_transcription|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "151347": {
148
+ "content": "<|code_prefix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "151348": {
156
+ "content": "<|code_middle|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "151349": {
164
+ "content": "<|code_suffix|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "151350": {
172
+ "content": "<think>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "</think>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151352": {
188
+ "content": "<tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151353": {
196
+ "content": "</tool_call>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151354": {
204
+ "content": "<tool_response>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "151355": {
212
+ "content": "</tool_response>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "151356": {
220
+ "content": "<arg_key>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "151357": {
228
+ "content": "</arg_key>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "151358": {
236
+ "content": "<arg_value>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "151359": {
244
+ "content": "</arg_value>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "151360": {
252
+ "content": "/nothink",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "151361": {
260
+ "content": "<|begin_of_box|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "151362": {
268
+ "content": "<|end_of_box|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "151363": {
276
+ "content": "<|image|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "151364": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ }
291
+ },
292
+ "additional_special_tokens": [
293
+ "<|endoftext|>",
294
+ "[MASK]",
295
+ "[gMASK]",
296
+ "[sMASK]",
297
+ "<sop>",
298
+ "<eop>",
299
+ "<|system|>",
300
+ "<|user|>",
301
+ "<|assistant|>",
302
+ "<|observation|>",
303
+ "<|begin_of_image|>",
304
+ "<|end_of_image|>",
305
+ "<|begin_of_video|>",
306
+ "<|end_of_video|>",
307
+ "<|begin_of_audio|>",
308
+ "<|end_of_audio|>",
309
+ "<|begin_of_transcription|>",
310
+ "<|end_of_transcription|>",
311
+ "<|code_prefix|>",
312
+ "<|code_middle|>",
313
+ "<|code_suffix|>",
314
+ "/nothink"
315
+ ],
316
+ "clean_up_tokenization_spaces": false,
317
+ "do_lower_case": false,
318
+ "eos_token": "<|endoftext|>",
319
+ "extra_special_tokens": {},
320
+ "model_max_length": 128000,
321
+ "pad_token": "<|endoftext|>",
322
+ "padding_side": "left",
323
+ "remove_space": false,
324
+ "tokenizer_class": "PreTrainedTokenizer"
325
+ }