demonwizard0 commited on
Commit
58e5259
·
verified ·
1 Parent(s): 102e185

Upload folder using huggingface_hub

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 +3 -0
  2. chat_template.jinja +137 -0
  3. config.json +405 -0
  4. generation_config.json +11 -0
  5. model-00001-of-00048.safetensors +3 -0
  6. model-00002-of-00048.safetensors +3 -0
  7. model-00003-of-00048.safetensors +3 -0
  8. model-00004-of-00048.safetensors +3 -0
  9. model-00005-of-00048.safetensors +3 -0
  10. model-00006-of-00048.safetensors +3 -0
  11. model-00007-of-00048.safetensors +3 -0
  12. model-00008-of-00048.safetensors +3 -0
  13. model-00009-of-00048.safetensors +3 -0
  14. model-00010-of-00048.safetensors +3 -0
  15. model-00011-of-00048.safetensors +3 -0
  16. model-00012-of-00048.safetensors +3 -0
  17. model-00013-of-00048.safetensors +3 -0
  18. model-00014-of-00048.safetensors +3 -0
  19. model-00015-of-00048.safetensors +3 -0
  20. model-00016-of-00048.safetensors +3 -0
  21. model-00017-of-00048.safetensors +3 -0
  22. model-00018-of-00048.safetensors +3 -0
  23. model-00019-of-00048.safetensors +3 -0
  24. model-00020-of-00048.safetensors +3 -0
  25. model-00021-of-00048.safetensors +3 -0
  26. model-00022-of-00048.safetensors +3 -0
  27. model-00023-of-00048.safetensors +3 -0
  28. model-00024-of-00048.safetensors +3 -0
  29. model-00025-of-00048.safetensors +3 -0
  30. model-00026-of-00048.safetensors +3 -0
  31. model-00027-of-00048.safetensors +3 -0
  32. model-00028-of-00048.safetensors +3 -0
  33. model-00029-of-00048.safetensors +3 -0
  34. model-00030-of-00048.safetensors +3 -0
  35. model-00031-of-00048.safetensors +3 -0
  36. model-00032-of-00048.safetensors +3 -0
  37. model-00033-of-00048.safetensors +3 -0
  38. model-00034-of-00048.safetensors +3 -0
  39. model-00035-of-00048.safetensors +3 -0
  40. model-00036-of-00048.safetensors +3 -0
  41. model-00037-of-00048.safetensors +3 -0
  42. model-00038-of-00048.safetensors +3 -0
  43. model-00039-of-00048.safetensors +3 -0
  44. model-00040-of-00048.safetensors +3 -0
  45. model-00041-of-00048.safetensors +3 -0
  46. model-00042-of-00048.safetensors +3 -0
  47. model-00043-of-00048.safetensors +3 -0
  48. model-00044-of-00048.safetensors +3 -0
  49. model-00045-of-00048.safetensors +3 -0
  50. model-00046-of-00048.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
37
+ temp_bench.png filter=lfs diff=lfs merge=lfs -text
38
+ bench.png filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% macro render_extra_keys(json_dict, handled_keys) %}
2
+ {%- if json_dict is mapping %}
3
+ {%- for json_key in json_dict if json_key not in handled_keys %}
4
+ {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
5
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
6
+ {%- else %}
7
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
8
+ {%- endif %}
9
+ {%- endfor %}
10
+ {%- endif %}
11
+ {% endmacro %}
12
+
13
+ {%- if messages[0]["role"] == "system" %}
14
+ {%- set system_message = messages[0]["content"] %}
15
+ {%- set loop_messages = messages[1:] %}
16
+ {%- else %}
17
+ {%- set loop_messages = messages %}
18
+ {%- endif %}
19
+
20
+ {%- if not tools is defined %}
21
+ {%- set tools = [] %}
22
+ {%- endif %}
23
+
24
+ {%- if system_message is defined %}
25
+ {{- "<|im_start|>system\n" + system_message }}
26
+ {%- else %}
27
+ {%- if tools is iterable and tools | length > 0 %}
28
+ {{- "<|im_start|>system\nYou are INTELLECT-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- if tools is iterable and tools | length > 0 %}
32
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
33
+ {{- "<tools>" }}
34
+ {%- for tool in tools %}
35
+ {%- if tool.function is defined %}
36
+ {%- set tool = tool.function %}
37
+ {%- endif %}
38
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
39
+ {%- if tool.description is defined %}
40
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
41
+ {%- endif %}
42
+ {{- '\n<parameters>' }}
43
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
44
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
45
+ {{- '\n<parameter>' }}
46
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
47
+ {%- if param_fields.type is defined %}
48
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
49
+ {%- endif %}
50
+ {%- if param_fields.description is defined %}
51
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
52
+ {%- endif %}
53
+ {%- set handled_keys = ['name', 'type', 'description'] %}
54
+ {{- render_extra_keys(param_fields, handled_keys) }}
55
+ {{- '\n</parameter>' }}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {% set handled_keys = ['type', 'properties'] %}
59
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
60
+ {{- '\n</parameters>' }}
61
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
62
+ {{- render_extra_keys(tool, handled_keys) }}
63
+ {{- '\n</function>' }}
64
+ {%- endfor %}
65
+ {{- "\n</tools>" }}
66
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
67
+ {%- endif %}
68
+ {%- if system_message is defined %}
69
+ {{- '<|im_end|>\n' }}
70
+ {%- else %}
71
+ {%- if tools is iterable and tools | length > 0 %}
72
+ {{- '<|im_end|>\n' }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {%- for message in loop_messages %}
76
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
77
+ {{- '<|im_start|>' + message.role }}
78
+ {%- if message.content is defined and message.content is string %}
79
+ {%- if message.reasoning_content is defined -%}
80
+ {%- if message.reasoning_content -%}
81
+ {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
82
+ {%- else -%}
83
+ {{ '\n<think></think>' }}
84
+ {%- endif -%}
85
+ {%- endif -%}
86
+ {{- '\n' + message.content | trim + '\n' }}
87
+ {%- endif %}
88
+ {%- for tool_call in message.tool_calls %}
89
+ {%- if tool_call.function is defined %}
90
+ {%- set tool_call = tool_call.function %}
91
+ {%- endif %}
92
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
93
+ {%- if tool_call.arguments is defined %}
94
+ {%- for args_name, args_value in tool_call.arguments|items %}
95
+ {{- '<parameter=' + args_name + '>\n' }}
96
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
97
+ {{- args_value }}
98
+ {{- '\n</parameter>\n' }}
99
+ {%- endfor %}
100
+ {%- endif %}
101
+ {{- '</function>\n</tool_call>' }}
102
+ {%- endfor %}
103
+ {{- '<|im_end|>\n' }}
104
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
105
+ {{- '<|im_start|>' + message.role }}
106
+ {%- if message.role == "assistant" and message.reasoning_content is defined %}
107
+ {%- if message.reasoning_content -%}
108
+ {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
109
+ {%- else -%}
110
+ {{ '\n<think></think>' }}
111
+ {%- endif -%}
112
+ {%- if message.content.strip() -%}
113
+ {{ '\n' + message.content.strip() }}
114
+ {%- endif -%}
115
+ {%- else %}
116
+ {{- '\n' + message.content }}
117
+ {%- endif %}
118
+ {{- '<|im_end|>' + '\n' }}
119
+ {%- elif message.role == "tool" %}
120
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
121
+ {{- '<|im_start|>user\n' }}
122
+ {%- endif %}
123
+ {{- '<tool_response>\n' }}
124
+ {{- message.content }}
125
+ {{- '\n</tool_response>\n' }}
126
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
127
+ {{- '<|im_end|>\n' }}
128
+ {%- elif loop.last %}
129
+ {{- '<|im_end|>\n' }}
130
+ {%- endif %}
131
+ {%- else %}
132
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
133
+ {%- endif %}
134
+ {%- endfor %}
135
+ {%- if add_generation_prompt %}
136
+ {{- '<|im_start|>assistant\n<think>' }}
137
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4MoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": [
9
+ 151334,
10
+ 151329
11
+ ],
12
+ "first_k_dense_replace": 1,
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10944,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "glm4_moe",
20
+ "moe_intermediate_size": 1408,
21
+ "n_group": 1,
22
+ "n_routed_experts": 128,
23
+ "n_shared_experts": 1,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 96,
26
+ "num_experts_per_tok": 8,
27
+ "num_hidden_layers": 46,
28
+ "num_key_value_heads": 8,
29
+ "num_nextn_predict_layers": 1,
30
+ "pad_token_id": 151329,
31
+ "partial_rotary_factor": 0.5,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 1000000,
35
+ "routed_scaling_factor": 1.0,
36
+ "tie_word_embeddings": false,
37
+ "topk_group": 1,
38
+ "transformers_version": "4.56.1",
39
+ "use_cache": false,
40
+ "use_grouped_mm": true,
41
+ "use_qk_norm": false,
42
+ "vocab_size": 151552,
43
+ "quantization_config": {
44
+ "config_groups": {
45
+ "group_0": {
46
+ "input_activations": {
47
+ "actorder": null,
48
+ "block_structure": null,
49
+ "dynamic": true,
50
+ "group_size": null,
51
+ "num_bits": 8,
52
+ "observer": null,
53
+ "observer_kwargs": {},
54
+ "strategy": "token",
55
+ "symmetric": true,
56
+ "type": "float"
57
+ },
58
+ "output_activations": null,
59
+ "targets": [
60
+ "Linear"
61
+ ],
62
+ "weights": {
63
+ "actorder": null,
64
+ "block_structure": null,
65
+ "dynamic": false,
66
+ "group_size": null,
67
+ "num_bits": 8,
68
+ "observer": "minmax",
69
+ "observer_kwargs": {},
70
+ "strategy": "channel",
71
+ "symmetric": true,
72
+ "type": "float"
73
+ }
74
+ }
75
+ },
76
+ "format": "float-quantized",
77
+ "ignore": [
78
+ "model.layers.38.self_attn.k_proj.bias",
79
+ "model.layers.39.self_attn.v_proj.bias",
80
+ "model.layers.2.mlp.gate",
81
+ "model.layers.10.post_attention_layernorm",
82
+ "model.layers.7.mlp.gate",
83
+ "model.layers.34.mlp.gate.e_score_correction_bias",
84
+ "model.layers.32.mlp.gate",
85
+ "model.layers.38.post_attention_layernorm",
86
+ "model.layers.1.post_attention_layernorm",
87
+ "model.layers.17.mlp.gate",
88
+ "model.layers.41.post_attention_layernorm",
89
+ "model.layers.41.self_attn.q_proj.bias",
90
+ "model.layers.27.mlp.gate",
91
+ "model.layers.40.mlp.gate.e_score_correction_bias",
92
+ "model.layers.10.mlp.gate.e_score_correction_bias",
93
+ "model.layers.18.input_layernorm",
94
+ "model.layers.8.mlp.gate.e_score_correction_bias",
95
+ "model.layers.17.self_attn.q_proj.bias",
96
+ "model.layers.1.self_attn.v_proj.bias",
97
+ "model.layers.22.mlp.gate.e_score_correction_bias",
98
+ "model.layers.1.mlp.gate.e_score_correction_bias",
99
+ "model.layers.25.self_attn.k_proj.bias",
100
+ "model.layers.17.post_attention_layernorm",
101
+ "model.layers.4.post_attention_layernorm",
102
+ "model.layers.31.self_attn.k_proj.bias",
103
+ "model.layers.24.self_attn.v_proj.bias",
104
+ "model.layers.42.mlp.gate",
105
+ "model.layers.25.self_attn.v_proj.bias",
106
+ "model.layers.35.self_attn.k_proj.bias",
107
+ "model.layers.4.mlp.gate",
108
+ "model.layers.15.mlp.gate",
109
+ "model.layers.24.mlp.gate.e_score_correction_bias",
110
+ "model.layers.23.post_attention_layernorm",
111
+ "model.layers.2.input_layernorm",
112
+ "model.layers.30.input_layernorm",
113
+ "model.layers.41.input_layernorm",
114
+ "model.layers.31.mlp.gate.e_score_correction_bias",
115
+ "model.layers.5.self_attn.v_proj.bias",
116
+ "model.layers.3.mlp.gate.e_score_correction_bias",
117
+ "model.layers.43.self_attn.k_proj.bias",
118
+ "model.layers.32.self_attn.q_proj.bias",
119
+ "model.layers.14.self_attn.q_proj.bias",
120
+ "model.layers.24.self_attn.q_proj.bias",
121
+ "model.layers.19.post_attention_layernorm",
122
+ "model.layers.9.self_attn.k_proj.bias",
123
+ "model.layers.31.input_layernorm",
124
+ "model.layers.11.self_attn.q_proj.bias",
125
+ "model.layers.11.mlp.gate.e_score_correction_bias",
126
+ "model.layers.15.self_attn.q_proj.bias",
127
+ "model.layers.35.input_layernorm",
128
+ "model.layers.14.input_layernorm",
129
+ "model.layers.19.mlp.gate.e_score_correction_bias",
130
+ "model.layers.13.mlp.gate",
131
+ "model.layers.6.self_attn.v_proj.bias",
132
+ "model.layers.11.mlp.gate",
133
+ "model.layers.23.self_attn.k_proj.bias",
134
+ "model.layers.26.self_attn.k_proj.bias",
135
+ "model.layers.16.self_attn.v_proj.bias",
136
+ "model.layers.28.mlp.gate.e_score_correction_bias",
137
+ "model.layers.23.input_layernorm",
138
+ "model.layers.31.self_attn.q_proj.bias",
139
+ "model.layers.14.mlp.gate.e_score_correction_bias",
140
+ "model.norm",
141
+ "model.layers.8.self_attn.k_proj.bias",
142
+ "model.layers.28.self_attn.k_proj.bias",
143
+ "model.layers.9.mlp.gate.e_score_correction_bias",
144
+ "model.layers.37.self_attn.k_proj.bias",
145
+ "model.layers.37.post_attention_layernorm",
146
+ "model.layers.28.post_attention_layernorm",
147
+ "model.layers.28.self_attn.v_proj.bias",
148
+ "model.layers.45.self_attn.q_proj.bias",
149
+ "model.layers.20.input_layernorm",
150
+ "model.layers.40.self_attn.k_proj.bias",
151
+ "model.layers.13.post_attention_layernorm",
152
+ "model.layers.17.self_attn.k_proj.bias",
153
+ "model.layers.33.mlp.gate.e_score_correction_bias",
154
+ "model.layers.41.self_attn.k_proj.bias",
155
+ "model.layers.31.post_attention_layernorm",
156
+ "model.layers.28.input_layernorm",
157
+ "model.layers.1.input_layernorm",
158
+ "model.layers.9.input_layernorm",
159
+ "model.layers.25.self_attn.q_proj.bias",
160
+ "model.layers.41.mlp.gate.e_score_correction_bias",
161
+ "model.layers.21.self_attn.q_proj.bias",
162
+ "model.layers.40.mlp.gate",
163
+ "model.layers.32.self_attn.k_proj.bias",
164
+ "model.layers.17.self_attn.v_proj.bias",
165
+ "model.layers.29.self_attn.q_proj.bias",
166
+ "model.layers.36.mlp.gate.e_score_correction_bias",
167
+ "model.layers.31.self_attn.v_proj.bias",
168
+ "model.layers.5.mlp.gate.e_score_correction_bias",
169
+ "model.layers.38.self_attn.v_proj.bias",
170
+ "model.layers.17.input_layernorm",
171
+ "model.layers.5.mlp.gate",
172
+ "model.layers.16.input_layernorm",
173
+ "model.layers.34.self_attn.q_proj.bias",
174
+ "model.layers.40.input_layernorm",
175
+ "model.layers.39.mlp.gate.e_score_correction_bias",
176
+ "model.layers.18.mlp.gate",
177
+ "model.layers.32.post_attention_layernorm",
178
+ "lm_head",
179
+ "model.layers.4.mlp.gate.e_score_correction_bias",
180
+ "model.layers.13.self_attn.k_proj.bias",
181
+ "model.layers.19.input_layernorm",
182
+ "model.layers.11.self_attn.v_proj.bias",
183
+ "model.layers.5.self_attn.q_proj.bias",
184
+ "model.layers.18.self_attn.k_proj.bias",
185
+ "model.layers.3.self_attn.v_proj.bias",
186
+ "model.layers.31.mlp.gate",
187
+ "model.layers.6.self_attn.q_proj.bias",
188
+ "model.layers.1.mlp.gate",
189
+ "model.layers.22.self_attn.q_proj.bias",
190
+ "model.layers.33.post_attention_layernorm",
191
+ "model.layers.21.self_attn.v_proj.bias",
192
+ "model.layers.8.self_attn.v_proj.bias",
193
+ "model.layers.29.self_attn.k_proj.bias",
194
+ "model.layers.12.self_attn.q_proj.bias",
195
+ "model.layers.27.self_attn.v_proj.bias",
196
+ "model.layers.45.self_attn.v_proj.bias",
197
+ "model.layers.34.self_attn.k_proj.bias",
198
+ "model.layers.39.self_attn.q_proj.bias",
199
+ "model.layers.29.self_attn.v_proj.bias",
200
+ "model.layers.2.post_attention_layernorm",
201
+ "model.layers.33.input_layernorm",
202
+ "model.layers.25.post_attention_layernorm",
203
+ "model.layers.11.self_attn.k_proj.bias",
204
+ "model.layers.7.input_layernorm",
205
+ "model.layers.16.self_attn.k_proj.bias",
206
+ "model.layers.38.mlp.gate.e_score_correction_bias",
207
+ "model.layers.23.mlp.gate",
208
+ "model.layers.18.self_attn.q_proj.bias",
209
+ "model.layers.22.self_attn.k_proj.bias",
210
+ "model.layers.10.mlp.gate",
211
+ "model.layers.27.self_attn.k_proj.bias",
212
+ "model.layers.30.self_attn.k_proj.bias",
213
+ "model.layers.13.self_attn.v_proj.bias",
214
+ "model.layers.43.post_attention_layernorm",
215
+ "model.layers.40.self_attn.q_proj.bias",
216
+ "model.layers.36.post_attention_layernorm",
217
+ "model.layers.36.self_attn.q_proj.bias",
218
+ "model.layers.9.self_attn.v_proj.bias",
219
+ "model.layers.34.self_attn.v_proj.bias",
220
+ "model.layers.41.self_attn.v_proj.bias",
221
+ "model.layers.42.post_attention_layernorm",
222
+ "model.layers.38.self_attn.q_proj.bias",
223
+ "model.layers.37.mlp.gate.e_score_correction_bias",
224
+ "model.layers.45.self_attn.k_proj.bias",
225
+ "model.layers.32.mlp.gate.e_score_correction_bias",
226
+ "model.layers.16.mlp.gate",
227
+ "model.layers.16.mlp.gate.e_score_correction_bias",
228
+ "model.layers.4.self_attn.v_proj.bias",
229
+ "model.layers.36.self_attn.k_proj.bias",
230
+ "model.layers.25.mlp.gate.e_score_correction_bias",
231
+ "model.layers.20.self_attn.k_proj.bias",
232
+ "model.layers.12.post_attention_layernorm",
233
+ "model.layers.29.mlp.gate.e_score_correction_bias",
234
+ "model.layers.4.input_layernorm",
235
+ "model.layers.37.mlp.gate",
236
+ "model.layers.0.input_layernorm",
237
+ "model.layers.42.self_attn.k_proj.bias",
238
+ "model.layers.0.self_attn.q_proj.bias",
239
+ "model.layers.15.self_attn.v_proj.bias",
240
+ "model.layers.15.input_layernorm",
241
+ "model.layers.6.post_attention_layernorm",
242
+ "model.layers.34.post_attention_layernorm",
243
+ "model.layers.5.input_layernorm",
244
+ "model.layers.29.post_attention_layernorm",
245
+ "model.layers.30.mlp.gate",
246
+ "model.layers.38.input_layernorm",
247
+ "model.layers.6.input_layernorm",
248
+ "model.layers.22.post_attention_layernorm",
249
+ "model.layers.19.self_attn.k_proj.bias",
250
+ "model.layers.7.self_attn.v_proj.bias",
251
+ "model.layers.0.self_attn.v_proj.bias",
252
+ "model.layers.34.input_layernorm",
253
+ "model.layers.19.self_attn.q_proj.bias",
254
+ "model.layers.37.input_layernorm",
255
+ "model.layers.3.self_attn.q_proj.bias",
256
+ "model.layers.2.self_attn.v_proj.bias",
257
+ "model.layers.5.post_attention_layernorm",
258
+ "model.layers.32.input_layernorm",
259
+ "model.layers.4.self_attn.k_proj.bias",
260
+ "model.layers.22.self_attn.v_proj.bias",
261
+ "model.layers.15.post_attention_layernorm",
262
+ "model.layers.10.self_attn.v_proj.bias",
263
+ "model.layers.9.mlp.gate",
264
+ "model.layers.7.self_attn.k_proj.bias",
265
+ "model.layers.32.self_attn.v_proj.bias",
266
+ "model.layers.33.self_attn.q_proj.bias",
267
+ "model.layers.27.mlp.gate.e_score_correction_bias",
268
+ "model.layers.7.post_attention_layernorm",
269
+ "model.layers.37.self_attn.v_proj.bias",
270
+ "model.layers.29.mlp.gate",
271
+ "model.layers.14.mlp.gate",
272
+ "model.layers.42.self_attn.q_proj.bias",
273
+ "model.layers.28.mlp.gate",
274
+ "model.layers.22.mlp.gate",
275
+ "model.layers.14.self_attn.v_proj.bias",
276
+ "model.layers.26.self_attn.q_proj.bias",
277
+ "model.layers.44.self_attn.q_proj.bias",
278
+ "model.layers.21.input_layernorm",
279
+ "model.layers.27.post_attention_layernorm",
280
+ "model.layers.24.self_attn.k_proj.bias",
281
+ "model.layers.19.self_attn.v_proj.bias",
282
+ "model.layers.26.self_attn.v_proj.bias",
283
+ "model.layers.45.mlp.gate.e_score_correction_bias",
284
+ "model.layers.42.input_layernorm",
285
+ "model.layers.15.self_attn.k_proj.bias",
286
+ "model.layers.6.mlp.gate",
287
+ "model.layers.33.self_attn.v_proj.bias",
288
+ "model.layers.44.self_attn.k_proj.bias",
289
+ "model.layers.7.mlp.gate.e_score_correction_bias",
290
+ "model.layers.45.mlp.gate",
291
+ "model.layers.12.input_layernorm",
292
+ "model.layers.24.post_attention_layernorm",
293
+ "model.layers.35.self_attn.v_proj.bias",
294
+ "model.layers.35.mlp.gate",
295
+ "model.layers.17.mlp.gate.e_score_correction_bias",
296
+ "model.layers.8.input_layernorm",
297
+ "model.layers.30.self_attn.q_proj.bias",
298
+ "model.layers.26.post_attention_layernorm",
299
+ "model.layers.8.self_attn.q_proj.bias",
300
+ "model.layers.3.post_attention_layernorm",
301
+ "model.layers.12.mlp.gate.e_score_correction_bias",
302
+ "model.layers.8.post_attention_layernorm",
303
+ "model.layers.8.mlp.gate",
304
+ "model.layers.6.mlp.gate.e_score_correction_bias",
305
+ "model.layers.33.self_attn.k_proj.bias",
306
+ "model.layers.3.self_attn.k_proj.bias",
307
+ "model.layers.29.input_layernorm",
308
+ "model.layers.42.self_attn.v_proj.bias",
309
+ "model.layers.35.self_attn.q_proj.bias",
310
+ "model.layers.2.mlp.gate.e_score_correction_bias",
311
+ "model.layers.13.input_layernorm",
312
+ "model.layers.6.self_attn.k_proj.bias",
313
+ "model.layers.16.post_attention_layernorm",
314
+ "model.embed_tokens",
315
+ "model.layers.23.self_attn.q_proj.bias",
316
+ "model.layers.12.self_attn.v_proj.bias",
317
+ "model.layers.13.self_attn.q_proj.bias",
318
+ "model.layers.9.self_attn.q_proj.bias",
319
+ "model.layers.20.mlp.gate",
320
+ "model.layers.39.post_attention_layernorm",
321
+ "model.layers.21.self_attn.k_proj.bias",
322
+ "model.layers.18.post_attention_layernorm",
323
+ "model.layers.39.mlp.gate",
324
+ "model.layers.35.mlp.gate.e_score_correction_bias",
325
+ "model.layers.43.mlp.gate.e_score_correction_bias",
326
+ "model.layers.13.mlp.gate.e_score_correction_bias",
327
+ "model.layers.44.self_attn.v_proj.bias",
328
+ "model.layers.20.post_attention_layernorm",
329
+ "model.layers.18.self_attn.v_proj.bias",
330
+ "model.layers.4.self_attn.q_proj.bias",
331
+ "model.layers.10.input_layernorm",
332
+ "model.layers.33.mlp.gate",
333
+ "model.layers.1.self_attn.q_proj.bias",
334
+ "model.layers.30.mlp.gate.e_score_correction_bias",
335
+ "model.layers.0.self_attn.k_proj.bias",
336
+ "model.layers.2.self_attn.q_proj.bias",
337
+ "model.layers.44.post_attention_layernorm",
338
+ "model.layers.36.input_layernorm",
339
+ "model.layers.40.self_attn.v_proj.bias",
340
+ "model.layers.35.post_attention_layernorm",
341
+ "model.layers.14.self_attn.k_proj.bias",
342
+ "model.layers.37.self_attn.q_proj.bias",
343
+ "model.layers.16.self_attn.q_proj.bias",
344
+ "model.layers.44.mlp.gate",
345
+ "model.layers.27.input_layernorm",
346
+ "model.layers.44.mlp.gate.e_score_correction_bias",
347
+ "model.layers.36.self_attn.v_proj.bias",
348
+ "model.layers.39.self_attn.k_proj.bias",
349
+ "model.layers.12.self_attn.k_proj.bias",
350
+ "model.layers.40.post_attention_layernorm",
351
+ "model.layers.25.mlp.gate",
352
+ "model.layers.24.input_layernorm",
353
+ "model.layers.38.mlp.gate",
354
+ "model.layers.11.post_attention_layernorm",
355
+ "model.layers.43.mlp.gate",
356
+ "model.layers.11.input_layernorm",
357
+ "model.layers.44.input_layernorm",
358
+ "model.layers.43.input_layernorm",
359
+ "model.layers.20.mlp.gate.e_score_correction_bias",
360
+ "model.layers.2.self_attn.k_proj.bias",
361
+ "model.layers.10.self_attn.k_proj.bias",
362
+ "model.layers.25.input_layernorm",
363
+ "model.layers.43.self_attn.v_proj.bias",
364
+ "model.layers.24.mlp.gate",
365
+ "model.layers.26.input_layernorm",
366
+ "model.layers.23.mlp.gate.e_score_correction_bias",
367
+ "model.layers.30.self_attn.v_proj.bias",
368
+ "model.layers.19.mlp.gate",
369
+ "model.layers.28.self_attn.q_proj.bias",
370
+ "model.layers.3.mlp.gate",
371
+ "model.layers.9.post_attention_layernorm",
372
+ "model.layers.21.post_attention_layernorm",
373
+ "model.layers.7.self_attn.q_proj.bias",
374
+ "model.layers.45.input_layernorm",
375
+ "model.layers.12.mlp.gate",
376
+ "model.layers.14.post_attention_layernorm",
377
+ "model.layers.5.self_attn.k_proj.bias",
378
+ "model.layers.42.mlp.gate.e_score_correction_bias",
379
+ "model.layers.43.self_attn.q_proj.bias",
380
+ "model.layers.20.self_attn.q_proj.bias",
381
+ "model.layers.18.mlp.gate.e_score_correction_bias",
382
+ "model.layers.1.self_attn.k_proj.bias",
383
+ "model.layers.21.mlp.gate",
384
+ "model.layers.26.mlp.gate.e_score_correction_bias",
385
+ "model.layers.30.post_attention_layernorm",
386
+ "model.layers.20.self_attn.v_proj.bias",
387
+ "model.layers.26.mlp.gate",
388
+ "model.layers.23.self_attn.v_proj.bias",
389
+ "model.layers.21.mlp.gate.e_score_correction_bias",
390
+ "model.layers.34.mlp.gate",
391
+ "model.layers.39.input_layernorm",
392
+ "model.layers.3.input_layernorm",
393
+ "model.layers.0.post_attention_layernorm",
394
+ "model.layers.45.post_attention_layernorm",
395
+ "model.layers.22.input_layernorm",
396
+ "model.layers.15.mlp.gate.e_score_correction_bias",
397
+ "model.layers.10.self_attn.q_proj.bias",
398
+ "model.layers.27.self_attn.q_proj.bias",
399
+ "model.layers.41.mlp.gate",
400
+ "model.layers.36.mlp.gate"
401
+ ],
402
+ "quant_method": "compressed-tensors",
403
+ "quantization_status": "compressed"
404
+ }
405
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151334,
5
+ 151329
6
+ ],
7
+ "pad_token_id": 151329,
8
+ "transformers_version": "4.56.1",
9
+ "use_cache": false,
10
+ "temperature": 0.6
11
+ }
model-00001-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad7ed680cfa783d074968531c03a3a6b327f9a14dd308d47e155fbfba837e391
3
+ size 3072488696
model-00002-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31134ba2ba75ac078dbbd8a42893cf6c7280cb623b2cb9989ce586486ed7103d
3
+ size 2452152448
model-00003-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba8ffa68103bc020c09e3f0f538f3392c4aa7cd630eb4b993bb08e3be08c3a1
3
+ size 2872229232
model-00004-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30db85e12546fce1f065fada018a7ecf9ab613b2dc4bdbd3d6d1891f81202639
3
+ size 2236605392
model-00005-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c3620829a859ccb00a96844690b0d4d8fb2eaa61ff1fa5b2bbaff5205f8d93
3
+ size 2236605392
model-00006-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3495d982e7e42f0cbfe2098f1a2ea1a426a5bd496605a81f4e6267ac9afc519
3
+ size 2236605392
model-00007-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44803f8e29c071fcbdc91a04e4cfb162039a6f54f5e43591b19731ca01a66630
3
+ size 2236605392
model-00008-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e837161a0df0088903f743d6e6b7f60274140b0fafa97c8924d02eff30de931
3
+ size 2236605392
model-00009-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538072cf91d99b86da4c6ed8df6ca87600f30c149bdf765e329239e10c74a15e
3
+ size 2236605392
model-00010-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319de84c8960c243c3c3a219850bb3b838abc410952c2da686fae0db6a68f574
3
+ size 2236605392
model-00011-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f539b6669f9631bb3ea5089d6701664b366441eacc51aeadcf1a950f5a4323
3
+ size 2236605392
model-00012-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcccdeee5b7c97d950da419fcffb638273ad4e9bac4f9ef60343a6afaa3135b2
3
+ size 2236605512
model-00013-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6c6ec6a39cfc2f65ec50473e62b70deba977816bd58700893555e5beba906f
3
+ size 2236606168
model-00014-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337fefa97828e21c9afc9ed5303e188b1f301f085f9a462aeb50712344099bd5
3
+ size 2236606168
model-00015-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4695d8299b6a6edde27e1d2a9b25b461ef740d56ee30f758cb0774744c2bc921
3
+ size 2236606168
model-00016-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99d72622b267d89ca9618f408cd7181f82330142eba4603e87366c7e1737ed2
3
+ size 2236606168
model-00017-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a485a36ce961061a956e94061849a15d40dd189af2c1fa1851c01fe8632a2f
3
+ size 2236606168
model-00018-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec443363292548580059c26781ab9417d341584dbf11da45f5003855f514f537
3
+ size 2236606168
model-00019-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fcdb0a7155a7663722c449bcd139083450d1dca6cc205e9ba595f71c433e1b
3
+ size 2236606168
model-00020-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7315ddb40147d2959c8564ce0b0badea8ab05bdba080e39756f725d8bd5a9e
3
+ size 2236606168
model-00021-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c5e37b3c3d052bc45269281c8866161897fd10f7a9840d55564525b9a91ab6
3
+ size 2236606168
model-00022-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5af69001113b7d052a6ea359d1627a0a1a63c0088f8be1cc63181d2e7335588
3
+ size 2236606168
model-00023-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4423188bf851a7eade8dba5c1898e1e952c38997c29abd691bc7a1dc7ec836
3
+ size 2236606168
model-00024-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf900632db49e9d85e16b9f5da7c171e2e7780ee4444ce4146864a07ef0a3057
3
+ size 2236606168
model-00025-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7403b3c695e0914be60205f4f5b9256d4eb929fea697413d681d6afbdd4885
3
+ size 2236606168
model-00026-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a4c57152f75423de77837b76674542a326174ac7fe5ba44e7a797718b0ced2
3
+ size 2236606168
model-00027-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97d64c47846d9543910f88ad5bb2a2df3ce548ecd6dedbe2b385225e89987a3
3
+ size 2236606168
model-00028-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892b2a46fcf50202d0beea4de969a676498905cfb5c181491cdc4c8a7686e459
3
+ size 2236606168
model-00029-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854f2a0d8e24c58533a9360d4806843c417cafea6af7cee70804a0fc7e93223b
3
+ size 2236606168
model-00030-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a001db9b0e668dd75cf81f54ac7553420d814d7a1c0663dc9fbe74cb1faf522
3
+ size 2236606168
model-00031-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a082b3fbc8f44c9a6ef89386a203e2d6ecdff54c2b08a18ec00db61ff09546e
3
+ size 2236606168
model-00032-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1042806a548d8ddaa0433bc0142c29e2f33eb0bc8646b88e3744e777a4b066f6
3
+ size 2236606168
model-00033-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bdbc8e863d8f1a868d41f10847fc9dde30c0c005637ae61e92cf610a22833e
3
+ size 2236606168
model-00034-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5f1687d8bd4c1233c8a645d84e6aff02b38cb53a24e508dd1c8f3eb0588daa
3
+ size 2236606168
model-00035-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485038fb9183982374a3990c38056feb98eed12bba0724417b643459b38f9b8c
3
+ size 2236606168
model-00036-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e8a6e437b15821b4d843c628f6ac0baa135f76fdc1429907f023eeeafe6d4b
3
+ size 2236606168
model-00037-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ad600305d62d48e1b6949988e95a8b98bafd8b41299fc840010d15f51f281f
3
+ size 2236606168
model-00038-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4007b31c2c365adca542e82f1d4821dd66e4616f7700f15dafd1f9a54e5d67
3
+ size 2236606168
model-00039-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb1c736f85b303a87fc5124ab4c1e3e9046fa841b19a9089fdeb6d2eea9eb1a
3
+ size 2236606168
model-00040-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d1399af85150fb4f979270db6e6fa7f6916f64aa18784b5fac4e23459626b8
3
+ size 2236606168
model-00041-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa6c6fe1947fd568a15ec12d76a6a366a15a1bd382e9f5ed9b2716a528f929f
3
+ size 2236606168
model-00042-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0260f6a873132fac9a2edebb3dadf53292ba2fedcf5f4002def3207cae002b09
3
+ size 2236606168
model-00043-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6487610b9dc74f6ddbec9342e0063a5c7e6e7885751c2e37704278861a1f7b60
3
+ size 2236606168
model-00044-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303decdda790a9db179f77eb2be9742bff949f1528d0b22d1298081456fe6122
3
+ size 2236606168
model-00045-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb7cdef65ab376bc2329980a9533b43d89dc9246835a38cdd10799341dfe82f
3
+ size 2236606168
model-00046-of-00048.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4aaf0be613de3629b616fa781d5a978528dea13bae54fda7062688c2247c40
3
+ size 2236606168