AntonV HF Staff commited on
Commit
31e9d81
·
verified ·
1 Parent(s): bbedbc2

Copy from casinca/tiny-mimo-v2-flash

Browse files
.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
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ ---
4
+
5
+ # tiny-mimo-v2-flash
6
+
7
+ A ~2.34B-parameter tiny random-weight checkpoint of [XiaomiMiMo/MiMo-V2-Flash](https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash), used for internal testing in Hugging Face `transformers` for the native HF implementation.
8
+
9
+ ## Configuration
10
+
11
+
12
+
13
+ | Hyperparameter | Value | Original MiMo |
14
+ |--------|-------|--------------|
15
+ | `num_hidden_layers` | 5 | 48 |
16
+ | `layer_types` | `[full, sliding×4]` | matches pattern |
17
+ | `mlp_layer_types` | `[dense, sparse×4]` | matches pattern (layer 0 dense, rest MoE) |
18
+ | `hidden_size` | 2048 | 4096 (**ratio 2.0**) |
19
+ | `intermediate_size` | 8192 | 16384 (**ratio 2.0**) |
20
+ | `moe_intermediate_size` | 1024 | 2048 (**ratio 2.0**) |
21
+ | `num_attention_heads` / `num_key_value_heads` | 16 / 1 | 64 / 4 (**ratio 4.0**) |
22
+ | `head_dim` / `v_head_dim` | 192 / 128 | 192 / 128 |
23
+ | `n_routed_experts` / `num_experts_per_tok` | 64 / 2 | 256 / 8 (**ratio 4.0**) |
24
+ | parameters | 2.34B | 300B |
25
+
chat_template.jinja ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if not add_generation_prompt is defined -%}
2
+ {%- set add_generation_prompt = false -%}
3
+ {%- endif -%}
4
+ {%- if not enable_thinking is defined -%}
5
+ {%- set enable_thinking = false -%}
6
+ {%- endif -%}
7
+ {%- if not keep_all_reasoning is defined -%}
8
+ {%- set keep_all_reasoning = false -%}
9
+ {%- endif -%}
10
+ {%- macro render_extra_keys(json_dict, handled_keys) -%}
11
+ {%- if json_dict is mapping %}
12
+ {%- for json_key in json_dict if json_key not in handled_keys %}
13
+ {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
14
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
15
+ {%- else %}
16
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
17
+ {%- endif %}
18
+ {%- endfor %}
19
+ {%- endif %}
20
+ {%- endmacro -%}
21
+ {%- if messages[0]["role"] == "system" %}
22
+ {%- set system_message = messages[0]["content"] %}
23
+ {%- set loop_messages = messages[1:] %}
24
+ {%- else %}
25
+ {%- set loop_messages = messages %}
26
+ {%- endif %}
27
+ {%- set ns = namespace(last_user_index=-1) %}
28
+ {%- for m in loop_messages %}
29
+ {%- if m.role == 'user' %}
30
+ {%- set ns.last_user_index = loop.index0 -%}
31
+ {%- endif %}
32
+ {%- endfor %}
33
+ {%- if not tools is defined %}
34
+ {%- set tools = [] %}
35
+ {%- endif %}
36
+ {%- if system_message is defined %}
37
+ {{- "<|im_start|>system\n" + system_message }}
38
+ {%- else %}
39
+ {{- "<|im_start|>system\nYou are MiMo, a helpful AI assistant engineered by Xiaomi." }}
40
+ {%- endif %}
41
+ {%- if tools is iterable and tools | length > 0 %}
42
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou have access to the following functions:\n\n" }}
43
+ {{- "<tools>" }}
44
+ {%- for tool in tools %}
45
+ {%- if tool.function is defined %}
46
+ {%- set tool = tool.function %}
47
+ {%- endif %}
48
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
49
+ {%- if tool.description is defined %}
50
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
51
+ {%- endif %}
52
+ {{- '\n<parameters>' }}
53
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
54
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
55
+ {{- '\n<parameter>' }}
56
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
57
+ {%- if param_fields.type is defined %}
58
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
59
+ {%- endif %}
60
+ {%- if param_fields.description is defined %}
61
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
62
+ {%- endif %}
63
+ {%- set handled_keys = ['name', 'type', 'description'] %}
64
+ {{- render_extra_keys(param_fields, handled_keys) }}
65
+ {{- '\n</parameter>' }}
66
+ {%- endfor %}
67
+ {%- endif %}
68
+ {%- set handled_keys = ['type', 'properties'] %}
69
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
70
+ {{- '\n</parameters>' }}
71
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
72
+ {{- render_extra_keys(tool, handled_keys) }}
73
+ {{- '\n</function>' }}
74
+ {%- endfor %}
75
+ {{- "\n</tools>" }}
76
+ {{- '\n\nFor each function call, output the function name and arguments in the following format:\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>value_1</parameter>\n<parameter=example_parameter_2>This is the value for the second parameter\nthat can span\nmultiple lines</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- DO NOT use function calls inside <think></think> tags.\n- The value enclosed between parameter tags is preserved exactly as-is, including newlines and spaces.\n</IMPORTANT>' }}
77
+ {%- endif %}
78
+ {{- '<|im_end|>' }}
79
+ {%- for message in loop_messages %}
80
+ {%- if message.content is string %}
81
+ {%- set content = message.content %}
82
+ {%- else %}
83
+ {%- set content = '' %}
84
+ {%- endif %}
85
+ {%- if message.role == "assistant" %}
86
+ {%- if message.reasoning_content is string %}
87
+ {%- set reasoning_content = message.reasoning_content %}
88
+ {%- else %}
89
+ {%- set reasoning_content = '' %}
90
+ {%- if '</think>' in content %}
91
+ {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
92
+ {%- set content = content.split('</think>')[-1] %}
93
+ {%- endif %}
94
+ {%- endif %}
95
+ {%- if (keep_all_reasoning or loop.index0 > ns.last_user_index) and reasoning_content -%}
96
+ {{- '<|im_start|>' + message.role + '\n<think>' + reasoning_content + '</think>' + content }}
97
+ {%- else %}
98
+ {{- '<|im_start|>' + message.role + '\n<think></think>' + content }}
99
+ {%- endif %}
100
+ {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
101
+ {%- for tool_call in message.tool_calls %}
102
+ {%- if tool_call.function is defined %}
103
+ {%- set tool_call = tool_call.function %}
104
+ {%- endif %}
105
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
106
+ {%- if tool_call.arguments is defined %}
107
+ {%- for args_name, args_value in tool_call.arguments|items %}
108
+ {{- '<parameter=' + args_name + '>' }}
109
+ {%- 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 %}
110
+ {{- args_value }}
111
+ {{- '</parameter>\n' }}
112
+ {%- endfor %}
113
+ {%- endif %}
114
+ {{- '</function>\n</tool_call>' }}
115
+ {%- endfor %}
116
+ {%- endif %}
117
+ {{- '<|im_end|>' }}
118
+ {%- elif message.role == "user" or message.role == "system"%}
119
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' }}
120
+ {%- elif message.role == "tool" %}
121
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
122
+ {{- '<|im_start|>tool\n' }}
123
+ {%- endif %}
124
+ {{- '<tool_response>\n' }}
125
+ {{- message.content }}
126
+ {{- '\n</tool_response>\n' }}
127
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
128
+ {{- '<|im_end|>' }}
129
+ {%- elif loop.last %}
130
+ {{- '<|im_end|>' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' }}
134
+ {%- endif %}
135
+ {%- endfor %}
136
+ {%- if add_generation_prompt %}
137
+ {{- '<|im_start|>assistant\n' }}
138
+ {%- if not enable_thinking -%}
139
+ {{- '<think></think>' -}}
140
+ {%- else -%}
141
+ {{- '' -}}
142
+ {%- endif -%}
143
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "attention_value_scale": 0.707,
5
+ "bos_token_id": null,
6
+ "eos_token_id": 151645,
7
+ "head_dim": 192,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8192,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "sliding_attention",
15
+ "sliding_attention",
16
+ "sliding_attention",
17
+ "sliding_attention"
18
+ ],
19
+ "max_position_embeddings": 512,
20
+ "mlp_layer_types": [
21
+ "dense",
22
+ "sparse",
23
+ "sparse",
24
+ "sparse",
25
+ "sparse"
26
+ ],
27
+ "model_type": "mimo_v2_flash",
28
+ "moe_intermediate_size": 1024,
29
+ "n_group": 1,
30
+ "n_routed_experts": 64,
31
+ "norm_topk_prob": true,
32
+ "num_attention_heads": 16,
33
+ "num_experts_per_tok": 2,
34
+ "num_hidden_layers": 5,
35
+ "num_key_value_heads": 1,
36
+ "pad_token_id": 151643,
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_parameters": {
39
+ "full_attention": {
40
+ "partial_rotary_factor": 0.334,
41
+ "rope_theta": 5000000.0,
42
+ "rope_type": "default"
43
+ },
44
+ "sliding_attention": {
45
+ "partial_rotary_factor": 0.334,
46
+ "rope_theta": 10000.0,
47
+ "rope_type": "default"
48
+ }
49
+ },
50
+ "routed_scaling_factor": 1.0,
51
+ "sliding_window": 128,
52
+ "tie_word_embeddings": false,
53
+ "topk_group": 1,
54
+ "transformers_version": "5.7.0.dev0",
55
+ "use_cache": true,
56
+ "v_head_dim": 128,
57
+ "vocab_size": 151669
58
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3f5a618c41b9ba418d56f7d2532f0577aecdb30e8694c426a399a4959f1b6c
3
+ size 1999644448
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d75a901bebd8146f8c3682300eeb3768458b6ace41e4738a96a0e2c644a0d4
3
+ size 1998137832
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532bebad37176d2276e8d860e4be8d0b040d6caac4aba9a82e24cbb923a19f15
3
+ size 684427968
model.safetensors.index.json ADDED
@@ -0,0 +1,823 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 4682110080
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.self_attn.attention_sink_bias": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00003.safetensors",
64
+ "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00003.safetensors",
76
+ "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00003.safetensors",
84
+ "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00003.safetensors",
86
+ "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00003.safetensors",
87
+ "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00003.safetensors",
89
+ "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00003.safetensors",
90
+ "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00003.safetensors",
92
+ "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00003.safetensors",
94
+ "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00003.safetensors",
95
+ "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00003.safetensors",
96
+ "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00003.safetensors",
97
+ "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00003.safetensors",
98
+ "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00003.safetensors",
100
+ "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00003.safetensors",
102
+ "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00003.safetensors",
103
+ "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00003.safetensors",
104
+ "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00003.safetensors",
105
+ "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00003.safetensors",
106
+ "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00003.safetensors",
107
+ "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00003.safetensors",
109
+ "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00003.safetensors",
110
+ "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00003.safetensors",
111
+ "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00003.safetensors",
112
+ "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00003.safetensors",
113
+ "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00003.safetensors",
114
+ "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00003.safetensors",
115
+ "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00003.safetensors",
126
+ "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00003.safetensors",
127
+ "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00003.safetensors",
128
+ "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00003.safetensors",
129
+ "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00003.safetensors",
130
+ "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00003.safetensors",
131
+ "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00003.safetensors",
132
+ "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00003.safetensors",
133
+ "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00003.safetensors",
134
+ "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00003.safetensors",
135
+ "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00003.safetensors",
136
+ "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00003.safetensors",
137
+ "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00003.safetensors",
138
+ "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00003.safetensors",
139
+ "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00003.safetensors",
140
+ "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00003.safetensors",
141
+ "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00003.safetensors",
142
+ "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00003.safetensors",
143
+ "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00003.safetensors",
144
+ "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00003.safetensors",
145
+ "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00003.safetensors",
146
+ "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00003.safetensors",
148
+ "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00003.safetensors",
149
+ "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00003.safetensors",
150
+ "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00003.safetensors",
151
+ "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00003.safetensors",
152
+ "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00003.safetensors",
153
+ "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00003.safetensors",
154
+ "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00003.safetensors",
155
+ "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00003.safetensors",
156
+ "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00003.safetensors",
157
+ "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00003.safetensors",
158
+ "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00003.safetensors",
159
+ "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00003.safetensors",
160
+ "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00003.safetensors",
161
+ "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00003.safetensors",
162
+ "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00003.safetensors",
163
+ "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00003.safetensors",
164
+ "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00003.safetensors",
165
+ "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00003.safetensors",
166
+ "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00003.safetensors",
167
+ "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00003.safetensors",
168
+ "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00003.safetensors",
169
+ "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00003.safetensors",
171
+ "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00003.safetensors",
174
+ "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00003.safetensors",
175
+ "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00003.safetensors",
176
+ "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00003.safetensors",
177
+ "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00003.safetensors",
178
+ "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00003.safetensors",
179
+ "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00003.safetensors",
180
+ "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00003.safetensors",
181
+ "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00003.safetensors",
182
+ "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00003.safetensors",
183
+ "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00003.safetensors",
184
+ "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00003.safetensors",
188
+ "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00003.safetensors",
189
+ "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00003.safetensors",
190
+ "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00003.safetensors",
191
+ "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00003.safetensors",
192
+ "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00003.safetensors",
193
+ "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00003.safetensors",
194
+ "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00003.safetensors",
195
+ "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00003.safetensors",
196
+ "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00003.safetensors",
197
+ "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.1.mlp.gate.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.1.mlp.gate.e_score_correction_bias": "model-00001-of-00003.safetensors",
215
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.2.self_attn.attention_sink_bias": "model-00001-of-00003.safetensors",
218
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.2.mlp.experts.4.up_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.2.mlp.experts.5.up_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.2.mlp.experts.6.up_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.2.mlp.experts.8.up_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.2.mlp.experts.9.up_proj.weight": "model-00001-of-00003.safetensors",
242
+ "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.2.mlp.experts.10.up_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.2.mlp.experts.11.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.2.mlp.experts.12.up_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.2.mlp.experts.13.up_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.2.mlp.experts.14.up_proj.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.2.mlp.experts.16.up_proj.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.2.mlp.experts.17.up_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.2.mlp.experts.18.up_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.2.mlp.experts.19.up_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.2.mlp.experts.20.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.2.mlp.experts.21.up_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.2.mlp.experts.22.up_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.2.mlp.experts.23.up_proj.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.2.mlp.experts.24.up_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.2.mlp.experts.25.up_proj.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.2.mlp.experts.26.up_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.2.mlp.experts.27.up_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.2.mlp.experts.28.up_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.2.mlp.experts.29.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.2.mlp.experts.30.up_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.2.mlp.experts.31.up_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00003.safetensors",
297
+ "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-00003.safetensors",
298
+ "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00003.safetensors",
299
+ "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-00003.safetensors",
300
+ "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00003.safetensors",
301
+ "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-00003.safetensors",
302
+ "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00003.safetensors",
303
+ "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-00003.safetensors",
304
+ "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00003.safetensors",
305
+ "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-00003.safetensors",
306
+ "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00003.safetensors",
307
+ "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00003.safetensors",
309
+ "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-00003.safetensors",
310
+ "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00003.safetensors",
311
+ "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00003.safetensors",
312
+ "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00003.safetensors",
313
+ "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-00003.safetensors",
314
+ "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00003.safetensors",
322
+ "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00003.safetensors",
324
+ "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00003.safetensors",
326
+ "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00003.safetensors",
327
+ "model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00003.safetensors",
329
+ "model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00003.safetensors",
332
+ "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00003.safetensors",
334
+ "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00003.safetensors",
336
+ "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00003.safetensors",
337
+ "model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00003.safetensors",
340
+ "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00003.safetensors",
342
+ "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00003.safetensors",
344
+ "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00003.safetensors",
345
+ "model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00003.safetensors",
346
+ "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00003.safetensors",
347
+ "model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00003.safetensors",
348
+ "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00003.safetensors",
349
+ "model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00003.safetensors",
350
+ "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
351
+ "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
352
+ "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
353
+ "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
354
+ "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
355
+ "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
356
+ "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00003.safetensors",
360
+ "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00003.safetensors",
361
+ "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00003.safetensors",
362
+ "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00003.safetensors",
364
+ "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00003.safetensors",
365
+ "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00003.safetensors",
367
+ "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00003.safetensors",
368
+ "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00003.safetensors",
369
+ "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00003.safetensors",
370
+ "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00003.safetensors",
371
+ "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00003.safetensors",
372
+ "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00003.safetensors",
373
+ "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00003.safetensors",
374
+ "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00003.safetensors",
376
+ "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00003.safetensors",
378
+ "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00003.safetensors",
379
+ "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00003.safetensors",
380
+ "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00003.safetensors",
381
+ "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00003.safetensors",
382
+ "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00003.safetensors",
383
+ "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00003.safetensors",
384
+ "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00003.safetensors",
385
+ "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00003.safetensors",
386
+ "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00003.safetensors",
387
+ "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00003.safetensors",
388
+ "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00003.safetensors",
389
+ "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00003.safetensors",
391
+ "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00003.safetensors",
392
+ "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00003.safetensors",
393
+ "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00003.safetensors",
394
+ "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00003.safetensors",
395
+ "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00003.safetensors",
396
+ "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00003.safetensors",
397
+ "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00003.safetensors",
398
+ "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00003.safetensors",
399
+ "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00003.safetensors",
400
+ "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00003.safetensors",
401
+ "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00003.safetensors",
402
+ "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00003.safetensors",
403
+ "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00003.safetensors",
404
+ "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00003.safetensors",
405
+ "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00003.safetensors",
406
+ "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00003.safetensors",
407
+ "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00003.safetensors",
408
+ "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00003.safetensors",
409
+ "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00003.safetensors",
411
+ "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00003.safetensors",
412
+ "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00003.safetensors",
413
+ "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00003.safetensors",
414
+ "model.layers.2.mlp.gate.weight": "model-00002-of-00003.safetensors",
415
+ "model.layers.2.mlp.gate.e_score_correction_bias": "model-00002-of-00003.safetensors",
416
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors",
417
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
418
+ "model.layers.3.self_attn.attention_sink_bias": "model-00002-of-00003.safetensors",
419
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
420
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
421
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
422
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
423
+ "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
424
+ "model.layers.3.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
425
+ "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
426
+ "model.layers.3.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
427
+ "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
428
+ "model.layers.3.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
429
+ "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
430
+ "model.layers.3.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
431
+ "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors",
432
+ "model.layers.3.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors",
433
+ "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors",
434
+ "model.layers.3.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors",
435
+ "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors",
436
+ "model.layers.3.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors",
437
+ "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors",
438
+ "model.layers.3.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors",
439
+ "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00002-of-00003.safetensors",
440
+ "model.layers.3.mlp.experts.8.up_proj.weight": "model-00002-of-00003.safetensors",
441
+ "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00002-of-00003.safetensors",
442
+ "model.layers.3.mlp.experts.9.up_proj.weight": "model-00002-of-00003.safetensors",
443
+ "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00002-of-00003.safetensors",
444
+ "model.layers.3.mlp.experts.10.up_proj.weight": "model-00002-of-00003.safetensors",
445
+ "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00002-of-00003.safetensors",
446
+ "model.layers.3.mlp.experts.11.up_proj.weight": "model-00002-of-00003.safetensors",
447
+ "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00002-of-00003.safetensors",
448
+ "model.layers.3.mlp.experts.12.up_proj.weight": "model-00002-of-00003.safetensors",
449
+ "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00002-of-00003.safetensors",
450
+ "model.layers.3.mlp.experts.13.up_proj.weight": "model-00002-of-00003.safetensors",
451
+ "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00002-of-00003.safetensors",
452
+ "model.layers.3.mlp.experts.14.up_proj.weight": "model-00002-of-00003.safetensors",
453
+ "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00002-of-00003.safetensors",
454
+ "model.layers.3.mlp.experts.15.up_proj.weight": "model-00002-of-00003.safetensors",
455
+ "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00002-of-00003.safetensors",
456
+ "model.layers.3.mlp.experts.16.up_proj.weight": "model-00002-of-00003.safetensors",
457
+ "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.layers.3.mlp.experts.17.up_proj.weight": "model-00002-of-00003.safetensors",
459
+ "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00002-of-00003.safetensors",
460
+ "model.layers.3.mlp.experts.18.up_proj.weight": "model-00002-of-00003.safetensors",
461
+ "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00002-of-00003.safetensors",
462
+ "model.layers.3.mlp.experts.19.up_proj.weight": "model-00002-of-00003.safetensors",
463
+ "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00002-of-00003.safetensors",
464
+ "model.layers.3.mlp.experts.20.up_proj.weight": "model-00002-of-00003.safetensors",
465
+ "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00002-of-00003.safetensors",
466
+ "model.layers.3.mlp.experts.21.up_proj.weight": "model-00002-of-00003.safetensors",
467
+ "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00002-of-00003.safetensors",
468
+ "model.layers.3.mlp.experts.22.up_proj.weight": "model-00002-of-00003.safetensors",
469
+ "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00002-of-00003.safetensors",
470
+ "model.layers.3.mlp.experts.23.up_proj.weight": "model-00002-of-00003.safetensors",
471
+ "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00002-of-00003.safetensors",
472
+ "model.layers.3.mlp.experts.24.up_proj.weight": "model-00002-of-00003.safetensors",
473
+ "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00002-of-00003.safetensors",
474
+ "model.layers.3.mlp.experts.25.up_proj.weight": "model-00002-of-00003.safetensors",
475
+ "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00002-of-00003.safetensors",
476
+ "model.layers.3.mlp.experts.26.up_proj.weight": "model-00002-of-00003.safetensors",
477
+ "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00002-of-00003.safetensors",
478
+ "model.layers.3.mlp.experts.27.up_proj.weight": "model-00002-of-00003.safetensors",
479
+ "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00002-of-00003.safetensors",
480
+ "model.layers.3.mlp.experts.28.up_proj.weight": "model-00002-of-00003.safetensors",
481
+ "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00002-of-00003.safetensors",
482
+ "model.layers.3.mlp.experts.29.up_proj.weight": "model-00002-of-00003.safetensors",
483
+ "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00002-of-00003.safetensors",
484
+ "model.layers.3.mlp.experts.30.up_proj.weight": "model-00002-of-00003.safetensors",
485
+ "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00002-of-00003.safetensors",
486
+ "model.layers.3.mlp.experts.31.up_proj.weight": "model-00002-of-00003.safetensors",
487
+ "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00002-of-00003.safetensors",
488
+ "model.layers.3.mlp.experts.32.up_proj.weight": "model-00002-of-00003.safetensors",
489
+ "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00002-of-00003.safetensors",
490
+ "model.layers.3.mlp.experts.33.up_proj.weight": "model-00002-of-00003.safetensors",
491
+ "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00002-of-00003.safetensors",
492
+ "model.layers.3.mlp.experts.34.up_proj.weight": "model-00002-of-00003.safetensors",
493
+ "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00002-of-00003.safetensors",
494
+ "model.layers.3.mlp.experts.35.up_proj.weight": "model-00002-of-00003.safetensors",
495
+ "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00002-of-00003.safetensors",
496
+ "model.layers.3.mlp.experts.36.up_proj.weight": "model-00002-of-00003.safetensors",
497
+ "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00002-of-00003.safetensors",
498
+ "model.layers.3.mlp.experts.37.up_proj.weight": "model-00002-of-00003.safetensors",
499
+ "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00002-of-00003.safetensors",
500
+ "model.layers.3.mlp.experts.38.up_proj.weight": "model-00002-of-00003.safetensors",
501
+ "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00002-of-00003.safetensors",
502
+ "model.layers.3.mlp.experts.39.up_proj.weight": "model-00002-of-00003.safetensors",
503
+ "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00002-of-00003.safetensors",
504
+ "model.layers.3.mlp.experts.40.up_proj.weight": "model-00002-of-00003.safetensors",
505
+ "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00002-of-00003.safetensors",
506
+ "model.layers.3.mlp.experts.41.up_proj.weight": "model-00002-of-00003.safetensors",
507
+ "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00002-of-00003.safetensors",
508
+ "model.layers.3.mlp.experts.42.up_proj.weight": "model-00002-of-00003.safetensors",
509
+ "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00002-of-00003.safetensors",
510
+ "model.layers.3.mlp.experts.43.up_proj.weight": "model-00002-of-00003.safetensors",
511
+ "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00002-of-00003.safetensors",
512
+ "model.layers.3.mlp.experts.44.up_proj.weight": "model-00002-of-00003.safetensors",
513
+ "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00002-of-00003.safetensors",
514
+ "model.layers.3.mlp.experts.45.up_proj.weight": "model-00002-of-00003.safetensors",
515
+ "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00002-of-00003.safetensors",
516
+ "model.layers.3.mlp.experts.46.up_proj.weight": "model-00002-of-00003.safetensors",
517
+ "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00002-of-00003.safetensors",
518
+ "model.layers.3.mlp.experts.47.up_proj.weight": "model-00002-of-00003.safetensors",
519
+ "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00002-of-00003.safetensors",
520
+ "model.layers.3.mlp.experts.48.up_proj.weight": "model-00002-of-00003.safetensors",
521
+ "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00002-of-00003.safetensors",
522
+ "model.layers.3.mlp.experts.49.up_proj.weight": "model-00002-of-00003.safetensors",
523
+ "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00002-of-00003.safetensors",
524
+ "model.layers.3.mlp.experts.50.up_proj.weight": "model-00002-of-00003.safetensors",
525
+ "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00002-of-00003.safetensors",
526
+ "model.layers.3.mlp.experts.51.up_proj.weight": "model-00002-of-00003.safetensors",
527
+ "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00002-of-00003.safetensors",
528
+ "model.layers.3.mlp.experts.52.up_proj.weight": "model-00002-of-00003.safetensors",
529
+ "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-00003.safetensors",
530
+ "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-00003.safetensors",
531
+ "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-00003.safetensors",
532
+ "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-00003.safetensors",
533
+ "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-00003.safetensors",
534
+ "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-00003.safetensors",
535
+ "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-00003.safetensors",
536
+ "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-00003.safetensors",
537
+ "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-00003.safetensors",
538
+ "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-00003.safetensors",
539
+ "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-00003.safetensors",
540
+ "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-00003.safetensors",
541
+ "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-00003.safetensors",
542
+ "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-00003.safetensors",
543
+ "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00002-of-00003.safetensors",
544
+ "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-00003.safetensors",
545
+ "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00002-of-00003.safetensors",
546
+ "model.layers.3.mlp.experts.61.up_proj.weight": "model-00002-of-00003.safetensors",
547
+ "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00002-of-00003.safetensors",
548
+ "model.layers.3.mlp.experts.62.up_proj.weight": "model-00002-of-00003.safetensors",
549
+ "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00002-of-00003.safetensors",
550
+ "model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-00003.safetensors",
551
+ "model.layers.3.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
552
+ "model.layers.3.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
553
+ "model.layers.3.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
554
+ "model.layers.3.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
555
+ "model.layers.3.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
556
+ "model.layers.3.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
557
+ "model.layers.3.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
558
+ "model.layers.3.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
559
+ "model.layers.3.mlp.experts.8.down_proj.weight": "model-00002-of-00003.safetensors",
560
+ "model.layers.3.mlp.experts.9.down_proj.weight": "model-00002-of-00003.safetensors",
561
+ "model.layers.3.mlp.experts.10.down_proj.weight": "model-00002-of-00003.safetensors",
562
+ "model.layers.3.mlp.experts.11.down_proj.weight": "model-00002-of-00003.safetensors",
563
+ "model.layers.3.mlp.experts.12.down_proj.weight": "model-00002-of-00003.safetensors",
564
+ "model.layers.3.mlp.experts.13.down_proj.weight": "model-00002-of-00003.safetensors",
565
+ "model.layers.3.mlp.experts.14.down_proj.weight": "model-00002-of-00003.safetensors",
566
+ "model.layers.3.mlp.experts.15.down_proj.weight": "model-00002-of-00003.safetensors",
567
+ "model.layers.3.mlp.experts.16.down_proj.weight": "model-00002-of-00003.safetensors",
568
+ "model.layers.3.mlp.experts.17.down_proj.weight": "model-00002-of-00003.safetensors",
569
+ "model.layers.3.mlp.experts.18.down_proj.weight": "model-00002-of-00003.safetensors",
570
+ "model.layers.3.mlp.experts.19.down_proj.weight": "model-00002-of-00003.safetensors",
571
+ "model.layers.3.mlp.experts.20.down_proj.weight": "model-00002-of-00003.safetensors",
572
+ "model.layers.3.mlp.experts.21.down_proj.weight": "model-00002-of-00003.safetensors",
573
+ "model.layers.3.mlp.experts.22.down_proj.weight": "model-00002-of-00003.safetensors",
574
+ "model.layers.3.mlp.experts.23.down_proj.weight": "model-00002-of-00003.safetensors",
575
+ "model.layers.3.mlp.experts.24.down_proj.weight": "model-00002-of-00003.safetensors",
576
+ "model.layers.3.mlp.experts.25.down_proj.weight": "model-00002-of-00003.safetensors",
577
+ "model.layers.3.mlp.experts.26.down_proj.weight": "model-00002-of-00003.safetensors",
578
+ "model.layers.3.mlp.experts.27.down_proj.weight": "model-00002-of-00003.safetensors",
579
+ "model.layers.3.mlp.experts.28.down_proj.weight": "model-00002-of-00003.safetensors",
580
+ "model.layers.3.mlp.experts.29.down_proj.weight": "model-00002-of-00003.safetensors",
581
+ "model.layers.3.mlp.experts.30.down_proj.weight": "model-00002-of-00003.safetensors",
582
+ "model.layers.3.mlp.experts.31.down_proj.weight": "model-00002-of-00003.safetensors",
583
+ "model.layers.3.mlp.experts.32.down_proj.weight": "model-00002-of-00003.safetensors",
584
+ "model.layers.3.mlp.experts.33.down_proj.weight": "model-00002-of-00003.safetensors",
585
+ "model.layers.3.mlp.experts.34.down_proj.weight": "model-00002-of-00003.safetensors",
586
+ "model.layers.3.mlp.experts.35.down_proj.weight": "model-00002-of-00003.safetensors",
587
+ "model.layers.3.mlp.experts.36.down_proj.weight": "model-00002-of-00003.safetensors",
588
+ "model.layers.3.mlp.experts.37.down_proj.weight": "model-00002-of-00003.safetensors",
589
+ "model.layers.3.mlp.experts.38.down_proj.weight": "model-00002-of-00003.safetensors",
590
+ "model.layers.3.mlp.experts.39.down_proj.weight": "model-00002-of-00003.safetensors",
591
+ "model.layers.3.mlp.experts.40.down_proj.weight": "model-00002-of-00003.safetensors",
592
+ "model.layers.3.mlp.experts.41.down_proj.weight": "model-00002-of-00003.safetensors",
593
+ "model.layers.3.mlp.experts.42.down_proj.weight": "model-00002-of-00003.safetensors",
594
+ "model.layers.3.mlp.experts.43.down_proj.weight": "model-00002-of-00003.safetensors",
595
+ "model.layers.3.mlp.experts.44.down_proj.weight": "model-00002-of-00003.safetensors",
596
+ "model.layers.3.mlp.experts.45.down_proj.weight": "model-00002-of-00003.safetensors",
597
+ "model.layers.3.mlp.experts.46.down_proj.weight": "model-00002-of-00003.safetensors",
598
+ "model.layers.3.mlp.experts.47.down_proj.weight": "model-00002-of-00003.safetensors",
599
+ "model.layers.3.mlp.experts.48.down_proj.weight": "model-00002-of-00003.safetensors",
600
+ "model.layers.3.mlp.experts.49.down_proj.weight": "model-00002-of-00003.safetensors",
601
+ "model.layers.3.mlp.experts.50.down_proj.weight": "model-00002-of-00003.safetensors",
602
+ "model.layers.3.mlp.experts.51.down_proj.weight": "model-00002-of-00003.safetensors",
603
+ "model.layers.3.mlp.experts.52.down_proj.weight": "model-00002-of-00003.safetensors",
604
+ "model.layers.3.mlp.experts.53.down_proj.weight": "model-00002-of-00003.safetensors",
605
+ "model.layers.3.mlp.experts.54.down_proj.weight": "model-00002-of-00003.safetensors",
606
+ "model.layers.3.mlp.experts.55.down_proj.weight": "model-00002-of-00003.safetensors",
607
+ "model.layers.3.mlp.experts.56.down_proj.weight": "model-00002-of-00003.safetensors",
608
+ "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-00003.safetensors",
609
+ "model.layers.3.mlp.experts.58.down_proj.weight": "model-00002-of-00003.safetensors",
610
+ "model.layers.3.mlp.experts.59.down_proj.weight": "model-00002-of-00003.safetensors",
611
+ "model.layers.3.mlp.experts.60.down_proj.weight": "model-00002-of-00003.safetensors",
612
+ "model.layers.3.mlp.experts.61.down_proj.weight": "model-00002-of-00003.safetensors",
613
+ "model.layers.3.mlp.experts.62.down_proj.weight": "model-00002-of-00003.safetensors",
614
+ "model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-00003.safetensors",
615
+ "model.layers.3.mlp.gate.weight": "model-00002-of-00003.safetensors",
616
+ "model.layers.3.mlp.gate.e_score_correction_bias": "model-00002-of-00003.safetensors",
617
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors",
618
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
619
+ "model.layers.4.self_attn.attention_sink_bias": "model-00002-of-00003.safetensors",
620
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
621
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
622
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
623
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
624
+ "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00002-of-00003.safetensors",
625
+ "model.layers.4.mlp.experts.0.up_proj.weight": "model-00002-of-00003.safetensors",
626
+ "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00002-of-00003.safetensors",
627
+ "model.layers.4.mlp.experts.1.up_proj.weight": "model-00002-of-00003.safetensors",
628
+ "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00002-of-00003.safetensors",
629
+ "model.layers.4.mlp.experts.2.up_proj.weight": "model-00002-of-00003.safetensors",
630
+ "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00002-of-00003.safetensors",
631
+ "model.layers.4.mlp.experts.3.up_proj.weight": "model-00002-of-00003.safetensors",
632
+ "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00002-of-00003.safetensors",
633
+ "model.layers.4.mlp.experts.4.up_proj.weight": "model-00002-of-00003.safetensors",
634
+ "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00002-of-00003.safetensors",
635
+ "model.layers.4.mlp.experts.5.up_proj.weight": "model-00002-of-00003.safetensors",
636
+ "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00002-of-00003.safetensors",
637
+ "model.layers.4.mlp.experts.6.up_proj.weight": "model-00002-of-00003.safetensors",
638
+ "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00002-of-00003.safetensors",
639
+ "model.layers.4.mlp.experts.7.up_proj.weight": "model-00002-of-00003.safetensors",
640
+ "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00002-of-00003.safetensors",
641
+ "model.layers.4.mlp.experts.8.up_proj.weight": "model-00002-of-00003.safetensors",
642
+ "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00002-of-00003.safetensors",
643
+ "model.layers.4.mlp.experts.9.up_proj.weight": "model-00002-of-00003.safetensors",
644
+ "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00002-of-00003.safetensors",
645
+ "model.layers.4.mlp.experts.10.up_proj.weight": "model-00002-of-00003.safetensors",
646
+ "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00002-of-00003.safetensors",
647
+ "model.layers.4.mlp.experts.11.up_proj.weight": "model-00002-of-00003.safetensors",
648
+ "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00002-of-00003.safetensors",
649
+ "model.layers.4.mlp.experts.12.up_proj.weight": "model-00002-of-00003.safetensors",
650
+ "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00002-of-00003.safetensors",
651
+ "model.layers.4.mlp.experts.13.up_proj.weight": "model-00002-of-00003.safetensors",
652
+ "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00002-of-00003.safetensors",
653
+ "model.layers.4.mlp.experts.14.up_proj.weight": "model-00002-of-00003.safetensors",
654
+ "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00002-of-00003.safetensors",
655
+ "model.layers.4.mlp.experts.15.up_proj.weight": "model-00002-of-00003.safetensors",
656
+ "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00002-of-00003.safetensors",
657
+ "model.layers.4.mlp.experts.16.up_proj.weight": "model-00002-of-00003.safetensors",
658
+ "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00002-of-00003.safetensors",
659
+ "model.layers.4.mlp.experts.17.up_proj.weight": "model-00002-of-00003.safetensors",
660
+ "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00002-of-00003.safetensors",
661
+ "model.layers.4.mlp.experts.18.up_proj.weight": "model-00002-of-00003.safetensors",
662
+ "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00002-of-00003.safetensors",
663
+ "model.layers.4.mlp.experts.19.up_proj.weight": "model-00002-of-00003.safetensors",
664
+ "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00002-of-00003.safetensors",
665
+ "model.layers.4.mlp.experts.20.up_proj.weight": "model-00002-of-00003.safetensors",
666
+ "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00002-of-00003.safetensors",
667
+ "model.layers.4.mlp.experts.21.up_proj.weight": "model-00002-of-00003.safetensors",
668
+ "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00002-of-00003.safetensors",
669
+ "model.layers.4.mlp.experts.22.up_proj.weight": "model-00002-of-00003.safetensors",
670
+ "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00002-of-00003.safetensors",
671
+ "model.layers.4.mlp.experts.23.up_proj.weight": "model-00002-of-00003.safetensors",
672
+ "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00002-of-00003.safetensors",
673
+ "model.layers.4.mlp.experts.24.up_proj.weight": "model-00002-of-00003.safetensors",
674
+ "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00002-of-00003.safetensors",
675
+ "model.layers.4.mlp.experts.25.up_proj.weight": "model-00002-of-00003.safetensors",
676
+ "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00002-of-00003.safetensors",
677
+ "model.layers.4.mlp.experts.26.up_proj.weight": "model-00002-of-00003.safetensors",
678
+ "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00002-of-00003.safetensors",
679
+ "model.layers.4.mlp.experts.27.up_proj.weight": "model-00002-of-00003.safetensors",
680
+ "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00002-of-00003.safetensors",
681
+ "model.layers.4.mlp.experts.28.up_proj.weight": "model-00002-of-00003.safetensors",
682
+ "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00002-of-00003.safetensors",
683
+ "model.layers.4.mlp.experts.29.up_proj.weight": "model-00002-of-00003.safetensors",
684
+ "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00002-of-00003.safetensors",
685
+ "model.layers.4.mlp.experts.30.up_proj.weight": "model-00002-of-00003.safetensors",
686
+ "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00002-of-00003.safetensors",
687
+ "model.layers.4.mlp.experts.31.up_proj.weight": "model-00002-of-00003.safetensors",
688
+ "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00002-of-00003.safetensors",
689
+ "model.layers.4.mlp.experts.32.up_proj.weight": "model-00002-of-00003.safetensors",
690
+ "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00002-of-00003.safetensors",
691
+ "model.layers.4.mlp.experts.33.up_proj.weight": "model-00002-of-00003.safetensors",
692
+ "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00002-of-00003.safetensors",
693
+ "model.layers.4.mlp.experts.34.up_proj.weight": "model-00002-of-00003.safetensors",
694
+ "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00002-of-00003.safetensors",
695
+ "model.layers.4.mlp.experts.35.up_proj.weight": "model-00002-of-00003.safetensors",
696
+ "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00002-of-00003.safetensors",
697
+ "model.layers.4.mlp.experts.36.up_proj.weight": "model-00002-of-00003.safetensors",
698
+ "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00002-of-00003.safetensors",
699
+ "model.layers.4.mlp.experts.37.up_proj.weight": "model-00002-of-00003.safetensors",
700
+ "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00002-of-00003.safetensors",
701
+ "model.layers.4.mlp.experts.38.up_proj.weight": "model-00002-of-00003.safetensors",
702
+ "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00002-of-00003.safetensors",
703
+ "model.layers.4.mlp.experts.39.up_proj.weight": "model-00002-of-00003.safetensors",
704
+ "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00002-of-00003.safetensors",
705
+ "model.layers.4.mlp.experts.40.up_proj.weight": "model-00002-of-00003.safetensors",
706
+ "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00002-of-00003.safetensors",
707
+ "model.layers.4.mlp.experts.41.up_proj.weight": "model-00002-of-00003.safetensors",
708
+ "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00002-of-00003.safetensors",
709
+ "model.layers.4.mlp.experts.42.up_proj.weight": "model-00002-of-00003.safetensors",
710
+ "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00002-of-00003.safetensors",
711
+ "model.layers.4.mlp.experts.43.up_proj.weight": "model-00002-of-00003.safetensors",
712
+ "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00002-of-00003.safetensors",
713
+ "model.layers.4.mlp.experts.44.up_proj.weight": "model-00002-of-00003.safetensors",
714
+ "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00002-of-00003.safetensors",
715
+ "model.layers.4.mlp.experts.45.up_proj.weight": "model-00002-of-00003.safetensors",
716
+ "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00002-of-00003.safetensors",
717
+ "model.layers.4.mlp.experts.46.up_proj.weight": "model-00002-of-00003.safetensors",
718
+ "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00002-of-00003.safetensors",
719
+ "model.layers.4.mlp.experts.47.up_proj.weight": "model-00002-of-00003.safetensors",
720
+ "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00002-of-00003.safetensors",
721
+ "model.layers.4.mlp.experts.48.up_proj.weight": "model-00002-of-00003.safetensors",
722
+ "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00002-of-00003.safetensors",
723
+ "model.layers.4.mlp.experts.49.up_proj.weight": "model-00002-of-00003.safetensors",
724
+ "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00002-of-00003.safetensors",
725
+ "model.layers.4.mlp.experts.50.up_proj.weight": "model-00002-of-00003.safetensors",
726
+ "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00002-of-00003.safetensors",
727
+ "model.layers.4.mlp.experts.51.up_proj.weight": "model-00002-of-00003.safetensors",
728
+ "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00002-of-00003.safetensors",
729
+ "model.layers.4.mlp.experts.52.up_proj.weight": "model-00002-of-00003.safetensors",
730
+ "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00002-of-00003.safetensors",
731
+ "model.layers.4.mlp.experts.53.up_proj.weight": "model-00002-of-00003.safetensors",
732
+ "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00002-of-00003.safetensors",
733
+ "model.layers.4.mlp.experts.54.up_proj.weight": "model-00002-of-00003.safetensors",
734
+ "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00002-of-00003.safetensors",
735
+ "model.layers.4.mlp.experts.55.up_proj.weight": "model-00002-of-00003.safetensors",
736
+ "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00002-of-00003.safetensors",
737
+ "model.layers.4.mlp.experts.56.up_proj.weight": "model-00002-of-00003.safetensors",
738
+ "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00002-of-00003.safetensors",
739
+ "model.layers.4.mlp.experts.57.up_proj.weight": "model-00002-of-00003.safetensors",
740
+ "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00002-of-00003.safetensors",
741
+ "model.layers.4.mlp.experts.58.up_proj.weight": "model-00002-of-00003.safetensors",
742
+ "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00002-of-00003.safetensors",
743
+ "model.layers.4.mlp.experts.59.up_proj.weight": "model-00002-of-00003.safetensors",
744
+ "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00002-of-00003.safetensors",
745
+ "model.layers.4.mlp.experts.60.up_proj.weight": "model-00002-of-00003.safetensors",
746
+ "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00002-of-00003.safetensors",
747
+ "model.layers.4.mlp.experts.61.up_proj.weight": "model-00002-of-00003.safetensors",
748
+ "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00002-of-00003.safetensors",
749
+ "model.layers.4.mlp.experts.62.up_proj.weight": "model-00002-of-00003.safetensors",
750
+ "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00002-of-00003.safetensors",
751
+ "model.layers.4.mlp.experts.63.up_proj.weight": "model-00002-of-00003.safetensors",
752
+ "model.layers.4.mlp.experts.0.down_proj.weight": "model-00002-of-00003.safetensors",
753
+ "model.layers.4.mlp.experts.1.down_proj.weight": "model-00002-of-00003.safetensors",
754
+ "model.layers.4.mlp.experts.2.down_proj.weight": "model-00002-of-00003.safetensors",
755
+ "model.layers.4.mlp.experts.3.down_proj.weight": "model-00002-of-00003.safetensors",
756
+ "model.layers.4.mlp.experts.4.down_proj.weight": "model-00002-of-00003.safetensors",
757
+ "model.layers.4.mlp.experts.5.down_proj.weight": "model-00002-of-00003.safetensors",
758
+ "model.layers.4.mlp.experts.6.down_proj.weight": "model-00002-of-00003.safetensors",
759
+ "model.layers.4.mlp.experts.7.down_proj.weight": "model-00002-of-00003.safetensors",
760
+ "model.layers.4.mlp.experts.8.down_proj.weight": "model-00002-of-00003.safetensors",
761
+ "model.layers.4.mlp.experts.9.down_proj.weight": "model-00002-of-00003.safetensors",
762
+ "model.layers.4.mlp.experts.10.down_proj.weight": "model-00002-of-00003.safetensors",
763
+ "model.layers.4.mlp.experts.11.down_proj.weight": "model-00002-of-00003.safetensors",
764
+ "model.layers.4.mlp.experts.12.down_proj.weight": "model-00002-of-00003.safetensors",
765
+ "model.layers.4.mlp.experts.13.down_proj.weight": "model-00002-of-00003.safetensors",
766
+ "model.layers.4.mlp.experts.14.down_proj.weight": "model-00002-of-00003.safetensors",
767
+ "model.layers.4.mlp.experts.15.down_proj.weight": "model-00002-of-00003.safetensors",
768
+ "model.layers.4.mlp.experts.16.down_proj.weight": "model-00002-of-00003.safetensors",
769
+ "model.layers.4.mlp.experts.17.down_proj.weight": "model-00002-of-00003.safetensors",
770
+ "model.layers.4.mlp.experts.18.down_proj.weight": "model-00002-of-00003.safetensors",
771
+ "model.layers.4.mlp.experts.19.down_proj.weight": "model-00002-of-00003.safetensors",
772
+ "model.layers.4.mlp.experts.20.down_proj.weight": "model-00002-of-00003.safetensors",
773
+ "model.layers.4.mlp.experts.21.down_proj.weight": "model-00002-of-00003.safetensors",
774
+ "model.layers.4.mlp.experts.22.down_proj.weight": "model-00002-of-00003.safetensors",
775
+ "model.layers.4.mlp.experts.23.down_proj.weight": "model-00002-of-00003.safetensors",
776
+ "model.layers.4.mlp.experts.24.down_proj.weight": "model-00002-of-00003.safetensors",
777
+ "model.layers.4.mlp.experts.25.down_proj.weight": "model-00002-of-00003.safetensors",
778
+ "model.layers.4.mlp.experts.26.down_proj.weight": "model-00002-of-00003.safetensors",
779
+ "model.layers.4.mlp.experts.27.down_proj.weight": "model-00002-of-00003.safetensors",
780
+ "model.layers.4.mlp.experts.28.down_proj.weight": "model-00002-of-00003.safetensors",
781
+ "model.layers.4.mlp.experts.29.down_proj.weight": "model-00002-of-00003.safetensors",
782
+ "model.layers.4.mlp.experts.30.down_proj.weight": "model-00002-of-00003.safetensors",
783
+ "model.layers.4.mlp.experts.31.down_proj.weight": "model-00002-of-00003.safetensors",
784
+ "model.layers.4.mlp.experts.32.down_proj.weight": "model-00002-of-00003.safetensors",
785
+ "model.layers.4.mlp.experts.33.down_proj.weight": "model-00002-of-00003.safetensors",
786
+ "model.layers.4.mlp.experts.34.down_proj.weight": "model-00002-of-00003.safetensors",
787
+ "model.layers.4.mlp.experts.35.down_proj.weight": "model-00002-of-00003.safetensors",
788
+ "model.layers.4.mlp.experts.36.down_proj.weight": "model-00002-of-00003.safetensors",
789
+ "model.layers.4.mlp.experts.37.down_proj.weight": "model-00002-of-00003.safetensors",
790
+ "model.layers.4.mlp.experts.38.down_proj.weight": "model-00002-of-00003.safetensors",
791
+ "model.layers.4.mlp.experts.39.down_proj.weight": "model-00002-of-00003.safetensors",
792
+ "model.layers.4.mlp.experts.40.down_proj.weight": "model-00002-of-00003.safetensors",
793
+ "model.layers.4.mlp.experts.41.down_proj.weight": "model-00002-of-00003.safetensors",
794
+ "model.layers.4.mlp.experts.42.down_proj.weight": "model-00002-of-00003.safetensors",
795
+ "model.layers.4.mlp.experts.43.down_proj.weight": "model-00002-of-00003.safetensors",
796
+ "model.layers.4.mlp.experts.44.down_proj.weight": "model-00002-of-00003.safetensors",
797
+ "model.layers.4.mlp.experts.45.down_proj.weight": "model-00002-of-00003.safetensors",
798
+ "model.layers.4.mlp.experts.46.down_proj.weight": "model-00002-of-00003.safetensors",
799
+ "model.layers.4.mlp.experts.47.down_proj.weight": "model-00002-of-00003.safetensors",
800
+ "model.layers.4.mlp.experts.48.down_proj.weight": "model-00002-of-00003.safetensors",
801
+ "model.layers.4.mlp.experts.49.down_proj.weight": "model-00003-of-00003.safetensors",
802
+ "model.layers.4.mlp.experts.50.down_proj.weight": "model-00003-of-00003.safetensors",
803
+ "model.layers.4.mlp.experts.51.down_proj.weight": "model-00003-of-00003.safetensors",
804
+ "model.layers.4.mlp.experts.52.down_proj.weight": "model-00003-of-00003.safetensors",
805
+ "model.layers.4.mlp.experts.53.down_proj.weight": "model-00003-of-00003.safetensors",
806
+ "model.layers.4.mlp.experts.54.down_proj.weight": "model-00003-of-00003.safetensors",
807
+ "model.layers.4.mlp.experts.55.down_proj.weight": "model-00003-of-00003.safetensors",
808
+ "model.layers.4.mlp.experts.56.down_proj.weight": "model-00003-of-00003.safetensors",
809
+ "model.layers.4.mlp.experts.57.down_proj.weight": "model-00003-of-00003.safetensors",
810
+ "model.layers.4.mlp.experts.58.down_proj.weight": "model-00003-of-00003.safetensors",
811
+ "model.layers.4.mlp.experts.59.down_proj.weight": "model-00003-of-00003.safetensors",
812
+ "model.layers.4.mlp.experts.60.down_proj.weight": "model-00003-of-00003.safetensors",
813
+ "model.layers.4.mlp.experts.61.down_proj.weight": "model-00003-of-00003.safetensors",
814
+ "model.layers.4.mlp.experts.62.down_proj.weight": "model-00003-of-00003.safetensors",
815
+ "model.layers.4.mlp.experts.63.down_proj.weight": "model-00003-of-00003.safetensors",
816
+ "model.layers.4.mlp.gate.weight": "model-00003-of-00003.safetensors",
817
+ "model.layers.4.mlp.gate.e_score_correction_bias": "model-00003-of-00003.safetensors",
818
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
819
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
820
+ "model.norm.weight": "model-00003-of-00003.safetensors",
821
+ "lm_head.weight": "model-00003-of-00003.safetensors"
822
+ }
823
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 262144,
11
+ "pad_token": "<|endoftext|>",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null
15
+ }