0xSero commited on
Commit
c3ab9c8
·
verified ·
1 Parent(s): 75982ce

Trinity-Large-Thinking pruned to 216/256 experts (15.6%% pruned) via REAP

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +159 -0
  3. config.json +108 -0
  4. configuration_afmoe.py +133 -0
  5. generation_config.json +9 -0
  6. model-00001.safetensors +3 -0
  7. model-00002.safetensors +3 -0
  8. model-00003.safetensors +3 -0
  9. model-00004.safetensors +3 -0
  10. model-00005.safetensors +3 -0
  11. model-00006.safetensors +3 -0
  12. model-00007.safetensors +3 -0
  13. model-00008.safetensors +3 -0
  14. model-00009.safetensors +3 -0
  15. model-00010.safetensors +3 -0
  16. model-00011.safetensors +3 -0
  17. model-00012.safetensors +3 -0
  18. model-00013.safetensors +3 -0
  19. model-00014.safetensors +3 -0
  20. model-00015.safetensors +3 -0
  21. model-00016.safetensors +3 -0
  22. model-00017.safetensors +3 -0
  23. model-00018.safetensors +3 -0
  24. model-00019.safetensors +3 -0
  25. model-00020.safetensors +3 -0
  26. model-00021.safetensors +3 -0
  27. model-00022.safetensors +3 -0
  28. model-00023.safetensors +3 -0
  29. model-00024.safetensors +3 -0
  30. model-00025.safetensors +3 -0
  31. model-00026.safetensors +3 -0
  32. model-00027.safetensors +3 -0
  33. model-00028.safetensors +3 -0
  34. model-00029.safetensors +3 -0
  35. model-00030.safetensors +3 -0
  36. model-00031.safetensors +3 -0
  37. model-00032.safetensors +3 -0
  38. model-00033.safetensors +3 -0
  39. model-00034.safetensors +3 -0
  40. model-00035.safetensors +3 -0
  41. model-00036.safetensors +3 -0
  42. model-00037.safetensors +3 -0
  43. model-00038.safetensors +3 -0
  44. model-00039.safetensors +3 -0
  45. model-00040.safetensors +3 -0
  46. model-00041.safetensors +3 -0
  47. model-00042.safetensors +3 -0
  48. model-00043.safetensors +3 -0
  49. model-00044.safetensors +3 -0
  50. model-00045.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <|begin_of_text|>{%- 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
+ {%- macro render_tool_call(raw_tool_call) -%}
14
+ {%- if raw_tool_call.function is defined and raw_tool_call.function is mapping %}
15
+ {%- set tool_call = raw_tool_call.function %}
16
+ {%- else %}
17
+ {%- set tool_call = raw_tool_call %}
18
+ {%- endif %}
19
+ {{- '<tool_call>\n<function=' + (tool_call.name | default('') | string) + '>\n' }}
20
+ {%- if tool_call.arguments is defined and tool_call.arguments is mapping %}
21
+ {%- for args_name, args_value in tool_call.arguments.items() %}
22
+ {{- '<parameter=' + (args_name | string) + '>\n' }}
23
+ {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}
24
+ {{- args_value | tojson | safe }}
25
+ {%- else %}
26
+ {{- args_value | string }}
27
+ {%- endif %}
28
+ {{- '\n</parameter>\n' }}
29
+ {%- endfor %}
30
+ {%- endif %}
31
+ {{- '</function>\n</tool_call>' }}
32
+ {%- endmacro -%}
33
+
34
+ {%- set system_message = none %}
35
+ {%- if messages and messages[0]["role"] == "system" %}
36
+ {%- set system_message = messages[0]["content"] %}
37
+ {%- set loop_messages = messages[1:] %}
38
+ {%- else %}
39
+ {%- set loop_messages = messages %}
40
+ {%- endif %}
41
+
42
+ {%- if not tools is defined %}
43
+ {%- set tools = [] %}
44
+ {%- endif %}
45
+ {%- set has_tools = tools is iterable and tools is not string and tools | length > 0 %}
46
+
47
+ {%- if system_message is not none or has_tools %}
48
+ {{- '<|im_start|>system\n' }}
49
+ {%- if system_message is not none %}
50
+ {{- system_message }}
51
+ {%- else %}
52
+ {{- "You are Trinity Large, a helpful assistant developed by Arcee AI, that can interact with a computer to solve tasks." }}
53
+ {%- endif %}
54
+ {%- if has_tools %}
55
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
56
+ {%- for tool in tools %}
57
+ {%- if tool.function is defined and tool.function is mapping %}
58
+ {%- set tool = tool.function %}
59
+ {%- endif %}
60
+ {{- '\n<function>\n<name>' ~ (tool.name | default('') | string) ~ '</name>' }}
61
+ {%- if tool.description is defined and tool.description is not none %}
62
+ {{- '\n<description>' ~ (tool.description | string | trim) ~ '</description>' }}
63
+ {%- endif %}
64
+ {{- '\n<parameters>' }}
65
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
66
+ {%- for param_name, param_fields in tool.parameters.properties.items() %}
67
+ {{- '\n<parameter>\n<name>' ~ (param_name | string) ~ '</name>' }}
68
+ {%- if param_fields is mapping and param_fields.type is defined and param_fields.type is not none %}
69
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
70
+ {%- endif %}
71
+ {%- if param_fields is mapping and param_fields.description is defined and param_fields.description is not none %}
72
+ {{- '\n<description>' ~ (param_fields.description | string | trim) ~ '</description>' }}
73
+ {%- endif %}
74
+ {%- if param_fields is mapping %}
75
+ {%- set handled_keys = ['name', 'type', 'description'] %}
76
+ {{- render_extra_keys(param_fields, handled_keys) }}
77
+ {%- endif %}
78
+ {{- '\n</parameter>' }}
79
+ {%- endfor %}
80
+ {%- endif %}
81
+ {%- if tool.parameters is defined %}
82
+ {%- set handled_keys = ['type', 'properties'] %}
83
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
84
+ {%- endif %}
85
+ {{- '\n</parameters>' }}
86
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
87
+ {{- render_extra_keys(tool, handled_keys) }}
88
+ {{- '\n</function>' }}
89
+ {%- endfor %}
90
+ {{- "\n</tools>" }}
91
+ {{- '\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>' }}
92
+ {%- endif %}
93
+ {{- '<|im_end|>\n' }}
94
+ {%- endif %}
95
+
96
+ {%- for message in loop_messages %}
97
+ {%- set role = message.role | default('') %}
98
+ {%- if role == "assistant" %}
99
+ {%- set content_str = '' if message.content is none else (message.content | string) %}
100
+ {%- set trimmed_content = content_str | trim %}
101
+
102
+ {%- set has_reasoning_content = message.reasoning_content is defined %}
103
+ {%- set has_reasoning = has_reasoning_content or (message.reasoning is defined) %}
104
+
105
+ {%- if has_reasoning_content %}
106
+ {%- set reasoning_value = message.reasoning_content %}
107
+ {%- elif message.reasoning is defined %}
108
+ {%- set reasoning_value = message.reasoning %}
109
+ {%- else %}
110
+ {%- set reasoning_value = none %}
111
+ {%- endif %}
112
+
113
+ {%- set has_tool_calls = message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls is not string and message.tool_calls | length > 0 %}
114
+
115
+ {{- '<|im_start|>assistant\n' }}
116
+ {%- if has_reasoning %}
117
+ {%- if reasoning_value %}
118
+ {{- '<think>' + (reasoning_value | string | trim) + '</think>' }}
119
+ {%- else %}
120
+ {{- '<think></think>' }}
121
+ {%- endif %}
122
+ {%- if trimmed_content %}
123
+ {{- '\n' + trimmed_content }}
124
+ {%- endif %}
125
+ {%- elif has_tool_calls %}
126
+ {%- if trimmed_content %}
127
+ {{- trimmed_content }}
128
+ {%- endif %}
129
+ {%- else %}
130
+ {{- content_str }}
131
+ {%- endif %}
132
+
133
+ {%- if has_tool_calls %}
134
+ {%- for tool_call in message.tool_calls %}
135
+ {%- set separator = '\n' if ((loop.first and (has_reasoning or trimmed_content)) or (not loop.first)) else '' -%}
136
+ {{- separator + render_tool_call(tool_call) }}
137
+ {%- endfor %}
138
+ {%- endif %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif role == "tool" or role == "observation" or role == "function" %}
141
+ {%- if loop.first or loop.previtem.role not in ["tool", "observation", "function"] %}
142
+ {{- '<|im_start|>user\n' }}
143
+ {%- endif %}
144
+ {{- '<tool_response>\n' }}
145
+ {{- '' if message.content is none else (message.content | string) }}
146
+ {{- '\n</tool_response>\n' }}
147
+ {%- if loop.last or loop.nextitem.role not in ["tool", "observation", "function"] %}
148
+ {{- '<|im_end|>\n' }}
149
+ {%- endif %}
150
+ {%- else %}
151
+ {{- '<|im_start|>' + (role | string) }}
152
+ {{- '\n' + ('' if message.content is none else (message.content | string)) }}
153
+ {{- '<|im_end|>\n' }}
154
+ {%- endif %}
155
+ {%- endfor %}
156
+
157
+ {%- if add_generation_prompt %}
158
+ {{- '<|im_start|>assistant\n<think>' }}
159
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AfmoeForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_afmoe.AfmoeConfig",
8
+ "AutoModel": "modeling_afmoe.AfmoeModel",
9
+ "AutoModelForCausalLM": "modeling_afmoe.AfmoeForCausalLM"
10
+ },
11
+ "dtype": "bfloat16",
12
+ "global_attn_every_n_layers": 4,
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 12288,
18
+ "layer_types": [
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "full_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "full_attention"
79
+ ],
80
+ "load_balance_coeff": 5e-05,
81
+ "max_position_embeddings": 262144,
82
+ "model_type": "afmoe",
83
+ "moe_intermediate_size": 3072,
84
+ "mup_enabled": true,
85
+ "n_group": 1,
86
+ "num_attention_heads": 48,
87
+ "num_dense_layers": 6,
88
+ "num_expert_groups": 1,
89
+ "num_experts": 216,
90
+ "num_experts_per_tok": 4,
91
+ "num_hidden_layers": 60,
92
+ "num_key_value_heads": 8,
93
+ "num_limited_groups": 1,
94
+ "num_shared_experts": 1,
95
+ "rms_norm_eps": 1e-05,
96
+ "rope_scaling": null,
97
+ "rope_theta": 10000,
98
+ "route_norm": true,
99
+ "route_scale": 2.448,
100
+ "score_func": "sigmoid",
101
+ "sliding_window": 4096,
102
+ "tie_word_embeddings": false,
103
+ "topk_group": 1,
104
+ "transformers_version": "4.57.1",
105
+ "use_cache": true,
106
+ "use_grouped_mm": true,
107
+ "vocab_size": 200192
108
+ }
configuration_afmoe.py ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
3
+ #
4
+ # Licensed under the Apache License, Version 2.0 (the "License");
5
+ # you may not use this file except in compliance with the License.
6
+ # You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+ from transformers.configuration_utils import PretrainedConfig
16
+ from transformers.modeling_rope_utils import rope_config_validation
17
+ from transformers.configuration_utils import layer_type_validation
18
+ from transformers.utils import logging
19
+
20
+ logger = logging.get_logger(__name__)
21
+
22
+ class AfmoeConfig(PretrainedConfig):
23
+ """
24
+ n_group (`int`, *optional*, defaults to 1):
25
+ Number of groups for routed experts.
26
+ topk_group (`int`, *optional*, defaults to 1):
27
+ Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
28
+ """
29
+ model_type = "afmoe"
30
+ base_model_pp_plan = {
31
+ "embed_tokens": (["input_ids"], ["inputs_embeds"]),
32
+ "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
33
+ "norm": (["hidden_states"], ["hidden_states"]),
34
+ }
35
+
36
+ def __init__(
37
+ self,
38
+ num_hidden_layers: int = 32,
39
+ vocab_size: int = 200192,
40
+ hidden_size: int = 2048,
41
+ intermediate_size: int = 6144,
42
+ moe_intermediate_size=1408,
43
+ num_dense_layers=1,
44
+ num_attention_heads=16,
45
+ num_key_value_heads=None,
46
+ head_dim=128,
47
+ hidden_act="silu",
48
+ max_position_embeddings=16384,
49
+ initializer_range=0.02,
50
+ rms_norm_eps=1e-5,
51
+ use_cache=True,
52
+ tie_word_embeddings=False,
53
+ rope_theta=10000.0,
54
+ rope_scaling=None,
55
+ num_experts=64,
56
+ num_experts_per_tok=6,
57
+ num_shared_experts=2,
58
+ num_expert_groups=1,
59
+ num_limited_groups=1,
60
+ score_func="sigmoid",
61
+ route_norm=True,
62
+ route_scale=1.0,
63
+ global_attn_every_n_layers=4,
64
+ sliding_window=1024,
65
+ mup_enabled=False,
66
+ layer_types=None,
67
+ attention_dropout: float = 0.0,
68
+ n_group: int = 1,
69
+ topk_group: int = 1,
70
+ **kwargs,
71
+ ):
72
+ self.vocab_size = vocab_size
73
+ self.max_position_embeddings = max_position_embeddings
74
+ self.hidden_size = hidden_size
75
+ self.intermediate_size = intermediate_size
76
+ self.num_hidden_layers = num_hidden_layers
77
+ self.num_dense_layers = num_dense_layers
78
+ self.num_attention_heads = num_attention_heads
79
+ self.head_dim = head_dim
80
+ self.hidden_act = hidden_act
81
+ self.initializer_range = initializer_range
82
+ self.rms_norm_eps = rms_norm_eps
83
+ self.use_cache = use_cache
84
+ self.rope_theta = rope_theta
85
+ self.rope_scaling = rope_scaling
86
+
87
+
88
+ # MoE specific
89
+ self.moe_intermediate_size = moe_intermediate_size
90
+ self.num_experts_per_tok = num_experts_per_tok
91
+ self.n_group = n_group
92
+ self.topk_group = topk_group
93
+ self.num_experts = num_experts
94
+ self.num_shared_experts = num_shared_experts
95
+ self.num_expert_groups = num_expert_groups
96
+ self.num_limited_groups = num_limited_groups
97
+ self.score_func = score_func
98
+ self.route_norm = route_norm
99
+ self.route_scale = route_scale
100
+
101
+
102
+ # Attention specific
103
+ self.attention_dropout = attention_dropout
104
+ self.global_attn_every_n_layers = global_attn_every_n_layers
105
+ self.sliding_window = sliding_window
106
+ self.layer_types = layer_types
107
+ if self.layer_types is None:
108
+ self.layer_types = [
109
+ "sliding_attention" if bool((i + 1) % global_attn_every_n_layers) else "full_attention" for i in range(self.num_hidden_layers)
110
+ ]
111
+ layer_type_validation(self.layer_types)
112
+
113
+ # muP specific
114
+ self.mup_enabled = mup_enabled
115
+
116
+ if num_key_value_heads is None:
117
+ num_key_value_heads = num_attention_heads
118
+
119
+ self.num_key_value_heads = num_key_value_heads
120
+
121
+
122
+ # Validate rope configs
123
+ if self.rope_scaling is not None and "type" in self.rope_scaling:
124
+ self.rope_scaling["rope_type"] = self.rope_scaling["type"]
125
+ rope_config_validation(self)
126
+
127
+ super().__init__(
128
+ tie_word_embeddings=tie_word_embeddings,
129
+ **kwargs,
130
+ )
131
+
132
+
133
+ __all__ = ["AfmoeConfig"]
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 12,
6
+ "transformers_version": "4.57.3",
7
+ "temperature": 0.8,
8
+ "top_p": 0.8
9
+ }
model-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd8a3cc805dd3ea7aa74f75868cd85822f0afea34c4f94c492b72c65b8af15d
3
+ size 5360493784
model-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e4e7f733cd6582137c9f08119ca26691bbc314220ce3af3a51280074b15cb2
3
+ size 5360356008
model-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbbb30e8a276de5137e97d4b95d8c7450262698cd0e932fd6f90d585fb2c344
3
+ size 5360355736
model-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d60471d21c292d57ef2095a4a32d2b7280a76c0c37c330f1f18f897c9459e14
3
+ size 5355418136
model-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b6186979edd8c9ae1709d4849a93a00037b799a90728f64e0c760303cd8ba1
3
+ size 5360355848
model-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0148725021fbc2c6603337fc188aab41d6a57b8719c0653c4df493d78d596eff
3
+ size 5355417968
model-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7259a2ded0dd44f041a76ccdf40415c0516b6906475245bdd5005a22cd9a006c
3
+ size 5360356072
model-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199041c7f6017b29b8a19a690a5013356a2e35b216026d21780cd550990e65bb
3
+ size 5355417768
model-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d0480511c4b6a84d6753c5ada5c2239c71c510ff18de54790896836e3ff108
3
+ size 5360356024
model-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a692d00b8ffc0f045646db46a3ec26a620410214b74f7978fd6b5a0d9713892e
3
+ size 5360355704
model-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9415043e5558ddcbf3a63ea10459b000992fb5b3bedb3e46795f9cb1095cdf1
3
+ size 5355418424
model-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b74548545423bfd7a21437a0ccc7907732a77962605ef6d011d7476d2dd1545
3
+ size 5360356104
model-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fac7b7fdffad874bb8b22109f889bcce8ef35797bef5953e582df42210d7ace
3
+ size 5355418304
model-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726c387732495dc8e0f2cf19f82129932a6f2407a02f83d1c6bed67dfc592640
3
+ size 5360356336
model-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97be8da6a5c0d7f200d965ac06062ef0bd8e82c5af63d676bd2c9a54cc587878
3
+ size 5355418064
model-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe15ccf1d6c9b9c4bdf5e6230629e2ef7796cb63e3a294af77d48a046dcd9f4a
3
+ size 5360356320
model-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a023e0d90deac8c0278dd28c3602a24ffa136eba0b0713c9cb5614a69415d13
3
+ size 5360355960
model-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8016b56c4c56df7d62cc6e4ef4de239f6bf93a5d0fe5ac4376565c60581251
3
+ size 5355418456
model-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262d142fcbd151ceec5f2d81cba2da58205f11049486c1eff63613dd6eb5bc7e
3
+ size 5360356080
model-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dcc9a34e7c3f20c1192e1b248dd241b9fa153e3768727a8ba700655738181b
3
+ size 5355418336
model-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f6b47d3a3ad8ea372e5382784226c449d2573c701a3d50648ba712ab807913
3
+ size 5360356296
model-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea1577db0da1f7553632ff8f2c29c7f8d748ccfe3a5723b650a155ace49ba10
3
+ size 5355418096
model-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98345f1bf8578a6eb64915723009bd55f539a3e5119f73e3142a4924e75306b7
3
+ size 5360356336
model-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49703085da342ab03bb06710b026b2dff87c6efb1a940b482afd1494ff1eb98
3
+ size 5360355936
model-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8c08ab4accb32f31105cc98278cbaa840a735fd2ef1c0018511e902f607d63
3
+ size 5355418472
model-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455dcc08abcd8da2c2a4f5cf42b745c21b12ef7d4c542510e031a01fd54d201b
3
+ size 5360356072
model-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56408ce7f0bcc6977eaf27be319e1f7032ea2bf0eaf3cfbb70a9c2edea801dad
3
+ size 5355418360
model-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be05fb0f0aad47f6ea80a440b30049c63ecbca7f63782cb9523515459b3717e0
3
+ size 5360356248
model-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3b49517cdc346f9f1b5b307276477167a4ef878002a6dd2e99529d4e89fdc3
3
+ size 5355418128
model-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c779ba856def73057efc535ef1fc5e7c5f082e1ef8d3bc00bac1001689f75716
3
+ size 5360356352
model-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf307e21b738fb5c7059e6cd605b7e5216f8df7e0e99c1f701e4d0caef00e1e
3
+ size 5355418112
model-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5154539c76729c8d02a240922d72b2b668af41404c2287281928a9bc20db9da
3
+ size 5360356280
model-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec388a6b1850cc4570c6f98b2e8f76686480e42eb0bc401fa294131d006706ac
3
+ size 5360356056
model-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377644117ca5f2d762d91a8534be72b11a703a4ba5b209c1e47dead8f8be21db
3
+ size 5355418392
model-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f794c8df17b3fcaed8703205ce36bf90f8f96a67ef7866a7e1c2201a60b5c38
3
+ size 5360356208
model-00036.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd5a9a20983c19de79bdc78d80778224be7b4d5252ed8141174c9cc4a94ec46
3
+ size 5355418160
model-00037.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f866471f89c16668fb5525354eca9298971eed578d8545d7a2bf5f86144788fd
3
+ size 5360356360
model-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcd4ca116947f5d9146c5ad32e7be1ec6ad5a5578dc002c1d3b1c9d87827699
3
+ size 5355418096
model-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97aadeb189ff7a057752a81b8a53b164af010b8ad538c318fcf9cd76f2359e23
3
+ size 5360356288
model-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ea3b83a2c88b920840aadff967be424d66ad5efd3951333041bfdbb481210e
3
+ size 5360356040
model-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b1ec268400a33cd0918fc40aecf94c91c99260f23516f5cfb6f1313165c1bb
3
+ size 5355418416
model-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001c9aba6352681e25bc5273fff06aca32876a0f2121a779d1fd2f233945cac9
3
+ size 5360356168
model-00043.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836ff1af0bfa793202d75464d1d6e5c2c0173cbfeaaa3d077c70c60272343ff5
3
+ size 5355418200
model-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789c2ff30ba31ed0987bb322ef9b6da2d02715d7925792c732badcd2292b0737
3
+ size 5360356360
model-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64d45e3b88083195b92f2defd0c94ac084dffdd003a99118dee1deb46e03218
3
+ size 5355418080