Hugging Face's logo

HelpingAI
/
Dhanishtha-2.0-preview-mlx

Text Generation
Transformers
Safetensors
qwen3
reasoning
intermediate-thinking
conversational
bilingual
text-generation-inference
4-bit precision
Model card Files
xet
Community
Abhaykoul commited on
Commit
200d4e9
·
verified ·
1 Parent(s): e7d708f

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. README.md +71 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +79 -0
  5. config.json +1006 -0
  6. generation_config.json +14 -0
  7. merges.txt +0 -0
  8. model-00001-of-00002.safetensors +3 -0
  9. model-00002-of-00002.safetensors +3 -0
  10. model.safetensors.index.json +1015 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +240 -0
  14. vocab.json +0 -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
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - hi
5
+ - zh
6
+ - es
7
+ - fr
8
+ - de
9
+ - ja
10
+ - ko
11
+ - ar
12
+ - pt
13
+ - ru
14
+ - it
15
+ - nl
16
+ - tr
17
+ - pl
18
+ - sv
19
+ - da
20
+ - 'no'
21
+ - fi
22
+ - he
23
+ - th
24
+ - vi
25
+ - id
26
+ - ms
27
+ - tl
28
+ - sw
29
+ - yo
30
+ - zu
31
+ - am
32
+ - bn
33
+ - gu
34
+ - kn
35
+ - ml
36
+ - mr
37
+ - ne
38
+ - or
39
+ - pa
40
+ - ta
41
+ - te
42
+ - ur
43
+ - multilingual
44
+ license: apache-2.0
45
+ base_model: HelpingAI/Dhanishtha-2.0-preview
46
+ tags:
47
+ - reasoning
48
+ - intermediate-thinking
49
+ - transformers
50
+ - conversational
51
+ - bilingual
52
+ - mlx
53
+ datasets:
54
+ - Abhaykoul/Dhanishtha-R1
55
+ - open-thoughts/OpenThoughts-114k
56
+ - Abhaykoul/Dhanishtha-2.0-SUPERTHINKER
57
+ - Abhaykoul/Dhanishtha-2.0
58
+ library_name: mlx
59
+ pipeline_tag: text-generation
60
+ widget:
61
+ - text: 'Solve this riddle step by step: I am taken from a mine, and shut up in a
62
+ wooden case, from which I am never released, and yet I am used by almost everybody.
63
+ What am I?'
64
+ example_title: Complex Riddle Solving
65
+ - text: Explain the philosophical implications of artificial consciousness and think
66
+ through different perspectives.
67
+ example_title: Philosophical Reasoning
68
+ - text: Help me understand quantum mechanics, but take your time to think through
69
+ the explanation.
70
+ example_title: Educational Explanation
71
+ ---
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for forward_message in messages %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- set message = messages[index] %}
21
+ {%- set current_content = message.content if message.content is not none else '' %}
22
+ {%- set tool_start = '<tool_response>' %}
23
+ {%- set tool_start_length = tool_start|length %}
24
+ {%- set start_of_message = current_content[:tool_start_length] %}
25
+ {%- set tool_end = '</tool_response>' %}
26
+ {%- set tool_end_length = tool_end|length %}
27
+ {%- set start_pos = (current_content|length) - tool_end_length %}
28
+ {%- if start_pos < 0 %}
29
+ {%- set start_pos = 0 %}
30
+ {%- endif %}
31
+ {%- set end_of_message = current_content[start_pos:] %}
32
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
33
+ {%- set ns.multi_step_tool = false %}
34
+ {%- set ns.last_query_index = index %}
35
+ {%- endif %}
36
+ {%- endfor %}
37
+ {%- for message in messages %}
38
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
39
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
40
+ {%- elif message.role == "assistant" %}
41
+ {{- '<|im_start|>' + message.role + '\n' }}
42
+ {%- if message.content %}
43
+ {{- message.content }}
44
+ {%- endif %}
45
+ {%- if message.tool_calls %}
46
+ {%- for tool_call in message.tool_calls %}
47
+ {%- if (loop.first and content) or (not loop.first) %}
48
+ {{- '\n' }}
49
+ {%- endif %}
50
+ {%- if tool_call.function %}
51
+ {%- set tool_call = tool_call.function %}
52
+ {%- endif %}
53
+ {{- '<tool_call>\n{"name": "' }}
54
+ {{- tool_call.name }}
55
+ {{- '", "arguments": ' }}
56
+ {%- if tool_call.arguments is string %}
57
+ {{- tool_call.arguments }}
58
+ {%- else %}
59
+ {{- tool_call.arguments | tojson }}
60
+ {%- endif %}
61
+ {{- '}\n</tool_call>' }}
62
+ {%- endfor %}
63
+ {%- endif %}
64
+ {{- '<|im_end|>\n' }}
65
+ {%- elif message.role == "tool" %}
66
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
67
+ {{- '<|im_start|>user' }}
68
+ {%- endif %}
69
+ {{- '\n<tool_response>\n' }}
70
+ {{- message.content }}
71
+ {{- '\n</tool_response>' }}
72
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
73
+ {{- '<|im_end|>\n' }}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- endfor %}
77
+ {%- if add_generation_prompt %}
78
+ {{- '<|im_start|>assistant\n' }}
79
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,1006 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 17408,
13
+ "max_position_embeddings": 40960,
14
+ "max_window_layers": 40,
15
+ "model_type": "qwen3",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 151654,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 4,
23
+ "model.embed_tokens": true,
24
+ "model.layers.0.self_attn.q_proj": true,
25
+ "model.layers.0.self_attn.k_proj": true,
26
+ "model.layers.0.self_attn.v_proj": true,
27
+ "model.layers.0.self_attn.o_proj": true,
28
+ "model.layers.0.self_attn.q_norm": false,
29
+ "model.layers.0.self_attn.k_norm": false,
30
+ "model.layers.0.self_attn.rope": false,
31
+ "model.layers.0.mlp.gate_proj": true,
32
+ "model.layers.0.mlp.down_proj": true,
33
+ "model.layers.0.mlp.up_proj": true,
34
+ "model.layers.0.input_layernorm": false,
35
+ "model.layers.0.post_attention_layernorm": false,
36
+ "model.layers.1.self_attn.q_proj": true,
37
+ "model.layers.1.self_attn.k_proj": true,
38
+ "model.layers.1.self_attn.v_proj": true,
39
+ "model.layers.1.self_attn.o_proj": true,
40
+ "model.layers.1.self_attn.q_norm": false,
41
+ "model.layers.1.self_attn.k_norm": false,
42
+ "model.layers.1.self_attn.rope": false,
43
+ "model.layers.1.mlp.gate_proj": true,
44
+ "model.layers.1.mlp.down_proj": true,
45
+ "model.layers.1.mlp.up_proj": true,
46
+ "model.layers.1.input_layernorm": false,
47
+ "model.layers.1.post_attention_layernorm": false,
48
+ "model.layers.2.self_attn.q_proj": true,
49
+ "model.layers.2.self_attn.k_proj": true,
50
+ "model.layers.2.self_attn.v_proj": true,
51
+ "model.layers.2.self_attn.o_proj": true,
52
+ "model.layers.2.self_attn.q_norm": false,
53
+ "model.layers.2.self_attn.k_norm": false,
54
+ "model.layers.2.self_attn.rope": false,
55
+ "model.layers.2.mlp.gate_proj": true,
56
+ "model.layers.2.mlp.down_proj": true,
57
+ "model.layers.2.mlp.up_proj": true,
58
+ "model.layers.2.input_layernorm": false,
59
+ "model.layers.2.post_attention_layernorm": false,
60
+ "model.layers.3.self_attn.q_proj": true,
61
+ "model.layers.3.self_attn.k_proj": true,
62
+ "model.layers.3.self_attn.v_proj": true,
63
+ "model.layers.3.self_attn.o_proj": true,
64
+ "model.layers.3.self_attn.q_norm": false,
65
+ "model.layers.3.self_attn.k_norm": false,
66
+ "model.layers.3.self_attn.rope": false,
67
+ "model.layers.3.mlp.gate_proj": true,
68
+ "model.layers.3.mlp.down_proj": true,
69
+ "model.layers.3.mlp.up_proj": true,
70
+ "model.layers.3.input_layernorm": false,
71
+ "model.layers.3.post_attention_layernorm": false,
72
+ "model.layers.4.self_attn.q_proj": true,
73
+ "model.layers.4.self_attn.k_proj": true,
74
+ "model.layers.4.self_attn.v_proj": true,
75
+ "model.layers.4.self_attn.o_proj": true,
76
+ "model.layers.4.self_attn.q_norm": false,
77
+ "model.layers.4.self_attn.k_norm": false,
78
+ "model.layers.4.self_attn.rope": false,
79
+ "model.layers.4.mlp.gate_proj": true,
80
+ "model.layers.4.mlp.down_proj": true,
81
+ "model.layers.4.mlp.up_proj": true,
82
+ "model.layers.4.input_layernorm": false,
83
+ "model.layers.4.post_attention_layernorm": false,
84
+ "model.layers.5.self_attn.q_proj": true,
85
+ "model.layers.5.self_attn.k_proj": true,
86
+ "model.layers.5.self_attn.v_proj": true,
87
+ "model.layers.5.self_attn.o_proj": true,
88
+ "model.layers.5.self_attn.q_norm": false,
89
+ "model.layers.5.self_attn.k_norm": false,
90
+ "model.layers.5.self_attn.rope": false,
91
+ "model.layers.5.mlp.gate_proj": true,
92
+ "model.layers.5.mlp.down_proj": true,
93
+ "model.layers.5.mlp.up_proj": true,
94
+ "model.layers.5.input_layernorm": false,
95
+ "model.layers.5.post_attention_layernorm": false,
96
+ "model.layers.6.self_attn.q_proj": true,
97
+ "model.layers.6.self_attn.k_proj": true,
98
+ "model.layers.6.self_attn.v_proj": true,
99
+ "model.layers.6.self_attn.o_proj": true,
100
+ "model.layers.6.self_attn.q_norm": false,
101
+ "model.layers.6.self_attn.k_norm": false,
102
+ "model.layers.6.self_attn.rope": false,
103
+ "model.layers.6.mlp.gate_proj": true,
104
+ "model.layers.6.mlp.down_proj": true,
105
+ "model.layers.6.mlp.up_proj": true,
106
+ "model.layers.6.input_layernorm": false,
107
+ "model.layers.6.post_attention_layernorm": false,
108
+ "model.layers.7.self_attn.q_proj": true,
109
+ "model.layers.7.self_attn.k_proj": true,
110
+ "model.layers.7.self_attn.v_proj": true,
111
+ "model.layers.7.self_attn.o_proj": true,
112
+ "model.layers.7.self_attn.q_norm": false,
113
+ "model.layers.7.self_attn.k_norm": false,
114
+ "model.layers.7.self_attn.rope": false,
115
+ "model.layers.7.mlp.gate_proj": true,
116
+ "model.layers.7.mlp.down_proj": true,
117
+ "model.layers.7.mlp.up_proj": true,
118
+ "model.layers.7.input_layernorm": false,
119
+ "model.layers.7.post_attention_layernorm": false,
120
+ "model.layers.8.self_attn.q_proj": true,
121
+ "model.layers.8.self_attn.k_proj": true,
122
+ "model.layers.8.self_attn.v_proj": true,
123
+ "model.layers.8.self_attn.o_proj": true,
124
+ "model.layers.8.self_attn.q_norm": false,
125
+ "model.layers.8.self_attn.k_norm": false,
126
+ "model.layers.8.self_attn.rope": false,
127
+ "model.layers.8.mlp.gate_proj": true,
128
+ "model.layers.8.mlp.down_proj": true,
129
+ "model.layers.8.mlp.up_proj": true,
130
+ "model.layers.8.input_layernorm": false,
131
+ "model.layers.8.post_attention_layernorm": false,
132
+ "model.layers.9.self_attn.q_proj": true,
133
+ "model.layers.9.self_attn.k_proj": true,
134
+ "model.layers.9.self_attn.v_proj": true,
135
+ "model.layers.9.self_attn.o_proj": true,
136
+ "model.layers.9.self_attn.q_norm": false,
137
+ "model.layers.9.self_attn.k_norm": false,
138
+ "model.layers.9.self_attn.rope": false,
139
+ "model.layers.9.mlp.gate_proj": true,
140
+ "model.layers.9.mlp.down_proj": true,
141
+ "model.layers.9.mlp.up_proj": true,
142
+ "model.layers.9.input_layernorm": false,
143
+ "model.layers.9.post_attention_layernorm": false,
144
+ "model.layers.10.self_attn.q_proj": true,
145
+ "model.layers.10.self_attn.k_proj": true,
146
+ "model.layers.10.self_attn.v_proj": true,
147
+ "model.layers.10.self_attn.o_proj": true,
148
+ "model.layers.10.self_attn.q_norm": false,
149
+ "model.layers.10.self_attn.k_norm": false,
150
+ "model.layers.10.self_attn.rope": false,
151
+ "model.layers.10.mlp.gate_proj": true,
152
+ "model.layers.10.mlp.down_proj": true,
153
+ "model.layers.10.mlp.up_proj": true,
154
+ "model.layers.10.input_layernorm": false,
155
+ "model.layers.10.post_attention_layernorm": false,
156
+ "model.layers.11.self_attn.q_proj": true,
157
+ "model.layers.11.self_attn.k_proj": true,
158
+ "model.layers.11.self_attn.v_proj": true,
159
+ "model.layers.11.self_attn.o_proj": true,
160
+ "model.layers.11.self_attn.q_norm": false,
161
+ "model.layers.11.self_attn.k_norm": false,
162
+ "model.layers.11.self_attn.rope": false,
163
+ "model.layers.11.mlp.gate_proj": true,
164
+ "model.layers.11.mlp.down_proj": true,
165
+ "model.layers.11.mlp.up_proj": true,
166
+ "model.layers.11.input_layernorm": false,
167
+ "model.layers.11.post_attention_layernorm": false,
168
+ "model.layers.12.self_attn.q_proj": true,
169
+ "model.layers.12.self_attn.k_proj": true,
170
+ "model.layers.12.self_attn.v_proj": true,
171
+ "model.layers.12.self_attn.o_proj": true,
172
+ "model.layers.12.self_attn.q_norm": false,
173
+ "model.layers.12.self_attn.k_norm": false,
174
+ "model.layers.12.self_attn.rope": false,
175
+ "model.layers.12.mlp.gate_proj": true,
176
+ "model.layers.12.mlp.down_proj": true,
177
+ "model.layers.12.mlp.up_proj": true,
178
+ "model.layers.12.input_layernorm": false,
179
+ "model.layers.12.post_attention_layernorm": false,
180
+ "model.layers.13.self_attn.q_proj": true,
181
+ "model.layers.13.self_attn.k_proj": true,
182
+ "model.layers.13.self_attn.v_proj": true,
183
+ "model.layers.13.self_attn.o_proj": true,
184
+ "model.layers.13.self_attn.q_norm": false,
185
+ "model.layers.13.self_attn.k_norm": false,
186
+ "model.layers.13.self_attn.rope": false,
187
+ "model.layers.13.mlp.gate_proj": true,
188
+ "model.layers.13.mlp.down_proj": true,
189
+ "model.layers.13.mlp.up_proj": true,
190
+ "model.layers.13.input_layernorm": false,
191
+ "model.layers.13.post_attention_layernorm": false,
192
+ "model.layers.14.self_attn.q_proj": true,
193
+ "model.layers.14.self_attn.k_proj": true,
194
+ "model.layers.14.self_attn.v_proj": true,
195
+ "model.layers.14.self_attn.o_proj": true,
196
+ "model.layers.14.self_attn.q_norm": false,
197
+ "model.layers.14.self_attn.k_norm": false,
198
+ "model.layers.14.self_attn.rope": false,
199
+ "model.layers.14.mlp.gate_proj": true,
200
+ "model.layers.14.mlp.down_proj": true,
201
+ "model.layers.14.mlp.up_proj": true,
202
+ "model.layers.14.input_layernorm": false,
203
+ "model.layers.14.post_attention_layernorm": false,
204
+ "model.layers.15.self_attn.q_proj": true,
205
+ "model.layers.15.self_attn.k_proj": true,
206
+ "model.layers.15.self_attn.v_proj": true,
207
+ "model.layers.15.self_attn.o_proj": true,
208
+ "model.layers.15.self_attn.q_norm": false,
209
+ "model.layers.15.self_attn.k_norm": false,
210
+ "model.layers.15.self_attn.rope": false,
211
+ "model.layers.15.mlp.gate_proj": true,
212
+ "model.layers.15.mlp.down_proj": true,
213
+ "model.layers.15.mlp.up_proj": true,
214
+ "model.layers.15.input_layernorm": false,
215
+ "model.layers.15.post_attention_layernorm": false,
216
+ "model.layers.16.self_attn.q_proj": true,
217
+ "model.layers.16.self_attn.k_proj": true,
218
+ "model.layers.16.self_attn.v_proj": true,
219
+ "model.layers.16.self_attn.o_proj": true,
220
+ "model.layers.16.self_attn.q_norm": false,
221
+ "model.layers.16.self_attn.k_norm": false,
222
+ "model.layers.16.self_attn.rope": false,
223
+ "model.layers.16.mlp.gate_proj": true,
224
+ "model.layers.16.mlp.down_proj": true,
225
+ "model.layers.16.mlp.up_proj": true,
226
+ "model.layers.16.input_layernorm": false,
227
+ "model.layers.16.post_attention_layernorm": false,
228
+ "model.layers.17.self_attn.q_proj": true,
229
+ "model.layers.17.self_attn.k_proj": true,
230
+ "model.layers.17.self_attn.v_proj": true,
231
+ "model.layers.17.self_attn.o_proj": true,
232
+ "model.layers.17.self_attn.q_norm": false,
233
+ "model.layers.17.self_attn.k_norm": false,
234
+ "model.layers.17.self_attn.rope": false,
235
+ "model.layers.17.mlp.gate_proj": true,
236
+ "model.layers.17.mlp.down_proj": true,
237
+ "model.layers.17.mlp.up_proj": true,
238
+ "model.layers.17.input_layernorm": false,
239
+ "model.layers.17.post_attention_layernorm": false,
240
+ "model.layers.18.self_attn.q_proj": true,
241
+ "model.layers.18.self_attn.k_proj": true,
242
+ "model.layers.18.self_attn.v_proj": true,
243
+ "model.layers.18.self_attn.o_proj": true,
244
+ "model.layers.18.self_attn.q_norm": false,
245
+ "model.layers.18.self_attn.k_norm": false,
246
+ "model.layers.18.self_attn.rope": false,
247
+ "model.layers.18.mlp.gate_proj": true,
248
+ "model.layers.18.mlp.down_proj": true,
249
+ "model.layers.18.mlp.up_proj": true,
250
+ "model.layers.18.input_layernorm": false,
251
+ "model.layers.18.post_attention_layernorm": false,
252
+ "model.layers.19.self_attn.q_proj": true,
253
+ "model.layers.19.self_attn.k_proj": true,
254
+ "model.layers.19.self_attn.v_proj": true,
255
+ "model.layers.19.self_attn.o_proj": true,
256
+ "model.layers.19.self_attn.q_norm": false,
257
+ "model.layers.19.self_attn.k_norm": false,
258
+ "model.layers.19.self_attn.rope": false,
259
+ "model.layers.19.mlp.gate_proj": true,
260
+ "model.layers.19.mlp.down_proj": true,
261
+ "model.layers.19.mlp.up_proj": true,
262
+ "model.layers.19.input_layernorm": false,
263
+ "model.layers.19.post_attention_layernorm": false,
264
+ "model.layers.20.self_attn.q_proj": true,
265
+ "model.layers.20.self_attn.k_proj": true,
266
+ "model.layers.20.self_attn.v_proj": true,
267
+ "model.layers.20.self_attn.o_proj": true,
268
+ "model.layers.20.self_attn.q_norm": false,
269
+ "model.layers.20.self_attn.k_norm": false,
270
+ "model.layers.20.self_attn.rope": false,
271
+ "model.layers.20.mlp.gate_proj": true,
272
+ "model.layers.20.mlp.down_proj": true,
273
+ "model.layers.20.mlp.up_proj": true,
274
+ "model.layers.20.input_layernorm": false,
275
+ "model.layers.20.post_attention_layernorm": false,
276
+ "model.layers.21.self_attn.q_proj": true,
277
+ "model.layers.21.self_attn.k_proj": true,
278
+ "model.layers.21.self_attn.v_proj": true,
279
+ "model.layers.21.self_attn.o_proj": true,
280
+ "model.layers.21.self_attn.q_norm": false,
281
+ "model.layers.21.self_attn.k_norm": false,
282
+ "model.layers.21.self_attn.rope": false,
283
+ "model.layers.21.mlp.gate_proj": true,
284
+ "model.layers.21.mlp.down_proj": true,
285
+ "model.layers.21.mlp.up_proj": true,
286
+ "model.layers.21.input_layernorm": false,
287
+ "model.layers.21.post_attention_layernorm": false,
288
+ "model.layers.22.self_attn.q_proj": true,
289
+ "model.layers.22.self_attn.k_proj": true,
290
+ "model.layers.22.self_attn.v_proj": true,
291
+ "model.layers.22.self_attn.o_proj": true,
292
+ "model.layers.22.self_attn.q_norm": false,
293
+ "model.layers.22.self_attn.k_norm": false,
294
+ "model.layers.22.self_attn.rope": false,
295
+ "model.layers.22.mlp.gate_proj": true,
296
+ "model.layers.22.mlp.down_proj": true,
297
+ "model.layers.22.mlp.up_proj": true,
298
+ "model.layers.22.input_layernorm": false,
299
+ "model.layers.22.post_attention_layernorm": false,
300
+ "model.layers.23.self_attn.q_proj": true,
301
+ "model.layers.23.self_attn.k_proj": true,
302
+ "model.layers.23.self_attn.v_proj": true,
303
+ "model.layers.23.self_attn.o_proj": true,
304
+ "model.layers.23.self_attn.q_norm": false,
305
+ "model.layers.23.self_attn.k_norm": false,
306
+ "model.layers.23.self_attn.rope": false,
307
+ "model.layers.23.mlp.gate_proj": true,
308
+ "model.layers.23.mlp.down_proj": true,
309
+ "model.layers.23.mlp.up_proj": true,
310
+ "model.layers.23.input_layernorm": false,
311
+ "model.layers.23.post_attention_layernorm": false,
312
+ "model.layers.24.self_attn.q_proj": true,
313
+ "model.layers.24.self_attn.k_proj": true,
314
+ "model.layers.24.self_attn.v_proj": true,
315
+ "model.layers.24.self_attn.o_proj": true,
316
+ "model.layers.24.self_attn.q_norm": false,
317
+ "model.layers.24.self_attn.k_norm": false,
318
+ "model.layers.24.self_attn.rope": false,
319
+ "model.layers.24.mlp.gate_proj": true,
320
+ "model.layers.24.mlp.down_proj": true,
321
+ "model.layers.24.mlp.up_proj": true,
322
+ "model.layers.24.input_layernorm": false,
323
+ "model.layers.24.post_attention_layernorm": false,
324
+ "model.layers.25.self_attn.q_proj": true,
325
+ "model.layers.25.self_attn.k_proj": true,
326
+ "model.layers.25.self_attn.v_proj": true,
327
+ "model.layers.25.self_attn.o_proj": true,
328
+ "model.layers.25.self_attn.q_norm": false,
329
+ "model.layers.25.self_attn.k_norm": false,
330
+ "model.layers.25.self_attn.rope": false,
331
+ "model.layers.25.mlp.gate_proj": true,
332
+ "model.layers.25.mlp.down_proj": true,
333
+ "model.layers.25.mlp.up_proj": true,
334
+ "model.layers.25.input_layernorm": false,
335
+ "model.layers.25.post_attention_layernorm": false,
336
+ "model.layers.26.self_attn.q_proj": true,
337
+ "model.layers.26.self_attn.k_proj": true,
338
+ "model.layers.26.self_attn.v_proj": true,
339
+ "model.layers.26.self_attn.o_proj": true,
340
+ "model.layers.26.self_attn.q_norm": false,
341
+ "model.layers.26.self_attn.k_norm": false,
342
+ "model.layers.26.self_attn.rope": false,
343
+ "model.layers.26.mlp.gate_proj": true,
344
+ "model.layers.26.mlp.down_proj": true,
345
+ "model.layers.26.mlp.up_proj": true,
346
+ "model.layers.26.input_layernorm": false,
347
+ "model.layers.26.post_attention_layernorm": false,
348
+ "model.layers.27.self_attn.q_proj": true,
349
+ "model.layers.27.self_attn.k_proj": true,
350
+ "model.layers.27.self_attn.v_proj": true,
351
+ "model.layers.27.self_attn.o_proj": true,
352
+ "model.layers.27.self_attn.q_norm": false,
353
+ "model.layers.27.self_attn.k_norm": false,
354
+ "model.layers.27.self_attn.rope": false,
355
+ "model.layers.27.mlp.gate_proj": true,
356
+ "model.layers.27.mlp.down_proj": true,
357
+ "model.layers.27.mlp.up_proj": true,
358
+ "model.layers.27.input_layernorm": false,
359
+ "model.layers.27.post_attention_layernorm": false,
360
+ "model.layers.28.self_attn.q_proj": true,
361
+ "model.layers.28.self_attn.k_proj": true,
362
+ "model.layers.28.self_attn.v_proj": true,
363
+ "model.layers.28.self_attn.o_proj": true,
364
+ "model.layers.28.self_attn.q_norm": false,
365
+ "model.layers.28.self_attn.k_norm": false,
366
+ "model.layers.28.self_attn.rope": false,
367
+ "model.layers.28.mlp.gate_proj": true,
368
+ "model.layers.28.mlp.down_proj": true,
369
+ "model.layers.28.mlp.up_proj": true,
370
+ "model.layers.28.input_layernorm": false,
371
+ "model.layers.28.post_attention_layernorm": false,
372
+ "model.layers.29.self_attn.q_proj": true,
373
+ "model.layers.29.self_attn.k_proj": true,
374
+ "model.layers.29.self_attn.v_proj": true,
375
+ "model.layers.29.self_attn.o_proj": true,
376
+ "model.layers.29.self_attn.q_norm": false,
377
+ "model.layers.29.self_attn.k_norm": false,
378
+ "model.layers.29.self_attn.rope": false,
379
+ "model.layers.29.mlp.gate_proj": true,
380
+ "model.layers.29.mlp.down_proj": true,
381
+ "model.layers.29.mlp.up_proj": true,
382
+ "model.layers.29.input_layernorm": false,
383
+ "model.layers.29.post_attention_layernorm": false,
384
+ "model.layers.30.self_attn.q_proj": true,
385
+ "model.layers.30.self_attn.k_proj": true,
386
+ "model.layers.30.self_attn.v_proj": true,
387
+ "model.layers.30.self_attn.o_proj": true,
388
+ "model.layers.30.self_attn.q_norm": false,
389
+ "model.layers.30.self_attn.k_norm": false,
390
+ "model.layers.30.self_attn.rope": false,
391
+ "model.layers.30.mlp.gate_proj": true,
392
+ "model.layers.30.mlp.down_proj": true,
393
+ "model.layers.30.mlp.up_proj": true,
394
+ "model.layers.30.input_layernorm": false,
395
+ "model.layers.30.post_attention_layernorm": false,
396
+ "model.layers.31.self_attn.q_proj": true,
397
+ "model.layers.31.self_attn.k_proj": true,
398
+ "model.layers.31.self_attn.v_proj": true,
399
+ "model.layers.31.self_attn.o_proj": true,
400
+ "model.layers.31.self_attn.q_norm": false,
401
+ "model.layers.31.self_attn.k_norm": false,
402
+ "model.layers.31.self_attn.rope": false,
403
+ "model.layers.31.mlp.gate_proj": true,
404
+ "model.layers.31.mlp.down_proj": true,
405
+ "model.layers.31.mlp.up_proj": true,
406
+ "model.layers.31.input_layernorm": false,
407
+ "model.layers.31.post_attention_layernorm": false,
408
+ "model.layers.32.self_attn.q_proj": true,
409
+ "model.layers.32.self_attn.k_proj": true,
410
+ "model.layers.32.self_attn.v_proj": true,
411
+ "model.layers.32.self_attn.o_proj": true,
412
+ "model.layers.32.self_attn.q_norm": false,
413
+ "model.layers.32.self_attn.k_norm": false,
414
+ "model.layers.32.self_attn.rope": false,
415
+ "model.layers.32.mlp.gate_proj": true,
416
+ "model.layers.32.mlp.down_proj": true,
417
+ "model.layers.32.mlp.up_proj": true,
418
+ "model.layers.32.input_layernorm": false,
419
+ "model.layers.32.post_attention_layernorm": false,
420
+ "model.layers.33.self_attn.q_proj": true,
421
+ "model.layers.33.self_attn.k_proj": true,
422
+ "model.layers.33.self_attn.v_proj": true,
423
+ "model.layers.33.self_attn.o_proj": true,
424
+ "model.layers.33.self_attn.q_norm": false,
425
+ "model.layers.33.self_attn.k_norm": false,
426
+ "model.layers.33.self_attn.rope": false,
427
+ "model.layers.33.mlp.gate_proj": true,
428
+ "model.layers.33.mlp.down_proj": true,
429
+ "model.layers.33.mlp.up_proj": true,
430
+ "model.layers.33.input_layernorm": false,
431
+ "model.layers.33.post_attention_layernorm": false,
432
+ "model.layers.34.self_attn.q_proj": true,
433
+ "model.layers.34.self_attn.k_proj": true,
434
+ "model.layers.34.self_attn.v_proj": true,
435
+ "model.layers.34.self_attn.o_proj": true,
436
+ "model.layers.34.self_attn.q_norm": false,
437
+ "model.layers.34.self_attn.k_norm": false,
438
+ "model.layers.34.self_attn.rope": false,
439
+ "model.layers.34.mlp.gate_proj": true,
440
+ "model.layers.34.mlp.down_proj": true,
441
+ "model.layers.34.mlp.up_proj": true,
442
+ "model.layers.34.input_layernorm": false,
443
+ "model.layers.34.post_attention_layernorm": false,
444
+ "model.layers.35.self_attn.q_proj": true,
445
+ "model.layers.35.self_attn.k_proj": true,
446
+ "model.layers.35.self_attn.v_proj": true,
447
+ "model.layers.35.self_attn.o_proj": true,
448
+ "model.layers.35.self_attn.q_norm": false,
449
+ "model.layers.35.self_attn.k_norm": false,
450
+ "model.layers.35.self_attn.rope": false,
451
+ "model.layers.35.mlp.gate_proj": true,
452
+ "model.layers.35.mlp.down_proj": true,
453
+ "model.layers.35.mlp.up_proj": true,
454
+ "model.layers.35.input_layernorm": false,
455
+ "model.layers.35.post_attention_layernorm": false,
456
+ "model.layers.36.self_attn.q_proj": true,
457
+ "model.layers.36.self_attn.k_proj": true,
458
+ "model.layers.36.self_attn.v_proj": true,
459
+ "model.layers.36.self_attn.o_proj": true,
460
+ "model.layers.36.self_attn.q_norm": false,
461
+ "model.layers.36.self_attn.k_norm": false,
462
+ "model.layers.36.self_attn.rope": false,
463
+ "model.layers.36.mlp.gate_proj": true,
464
+ "model.layers.36.mlp.down_proj": true,
465
+ "model.layers.36.mlp.up_proj": true,
466
+ "model.layers.36.input_layernorm": false,
467
+ "model.layers.36.post_attention_layernorm": false,
468
+ "model.layers.37.self_attn.q_proj": true,
469
+ "model.layers.37.self_attn.k_proj": true,
470
+ "model.layers.37.self_attn.v_proj": true,
471
+ "model.layers.37.self_attn.o_proj": true,
472
+ "model.layers.37.self_attn.q_norm": false,
473
+ "model.layers.37.self_attn.k_norm": false,
474
+ "model.layers.37.self_attn.rope": false,
475
+ "model.layers.37.mlp.gate_proj": true,
476
+ "model.layers.37.mlp.down_proj": true,
477
+ "model.layers.37.mlp.up_proj": true,
478
+ "model.layers.37.input_layernorm": false,
479
+ "model.layers.37.post_attention_layernorm": false,
480
+ "model.layers.38.self_attn.q_proj": true,
481
+ "model.layers.38.self_attn.k_proj": true,
482
+ "model.layers.38.self_attn.v_proj": true,
483
+ "model.layers.38.self_attn.o_proj": true,
484
+ "model.layers.38.self_attn.q_norm": false,
485
+ "model.layers.38.self_attn.k_norm": false,
486
+ "model.layers.38.self_attn.rope": false,
487
+ "model.layers.38.mlp.gate_proj": true,
488
+ "model.layers.38.mlp.down_proj": true,
489
+ "model.layers.38.mlp.up_proj": true,
490
+ "model.layers.38.input_layernorm": false,
491
+ "model.layers.38.post_attention_layernorm": false,
492
+ "model.layers.39.self_attn.q_proj": true,
493
+ "model.layers.39.self_attn.k_proj": true,
494
+ "model.layers.39.self_attn.v_proj": true,
495
+ "model.layers.39.self_attn.o_proj": true,
496
+ "model.layers.39.self_attn.q_norm": false,
497
+ "model.layers.39.self_attn.k_norm": false,
498
+ "model.layers.39.self_attn.rope": false,
499
+ "model.layers.39.mlp.gate_proj": true,
500
+ "model.layers.39.mlp.down_proj": true,
501
+ "model.layers.39.mlp.up_proj": true,
502
+ "model.layers.39.input_layernorm": false,
503
+ "model.layers.39.post_attention_layernorm": false,
504
+ "model.norm": false,
505
+ "lm_head": true
506
+ },
507
+ "quantization_config": {
508
+ "group_size": 64,
509
+ "bits": 4,
510
+ "model.embed_tokens": true,
511
+ "model.layers.0.self_attn.q_proj": true,
512
+ "model.layers.0.self_attn.k_proj": true,
513
+ "model.layers.0.self_attn.v_proj": true,
514
+ "model.layers.0.self_attn.o_proj": true,
515
+ "model.layers.0.self_attn.q_norm": false,
516
+ "model.layers.0.self_attn.k_norm": false,
517
+ "model.layers.0.self_attn.rope": false,
518
+ "model.layers.0.mlp.gate_proj": true,
519
+ "model.layers.0.mlp.down_proj": true,
520
+ "model.layers.0.mlp.up_proj": true,
521
+ "model.layers.0.input_layernorm": false,
522
+ "model.layers.0.post_attention_layernorm": false,
523
+ "model.layers.1.self_attn.q_proj": true,
524
+ "model.layers.1.self_attn.k_proj": true,
525
+ "model.layers.1.self_attn.v_proj": true,
526
+ "model.layers.1.self_attn.o_proj": true,
527
+ "model.layers.1.self_attn.q_norm": false,
528
+ "model.layers.1.self_attn.k_norm": false,
529
+ "model.layers.1.self_attn.rope": false,
530
+ "model.layers.1.mlp.gate_proj": true,
531
+ "model.layers.1.mlp.down_proj": true,
532
+ "model.layers.1.mlp.up_proj": true,
533
+ "model.layers.1.input_layernorm": false,
534
+ "model.layers.1.post_attention_layernorm": false,
535
+ "model.layers.2.self_attn.q_proj": true,
536
+ "model.layers.2.self_attn.k_proj": true,
537
+ "model.layers.2.self_attn.v_proj": true,
538
+ "model.layers.2.self_attn.o_proj": true,
539
+ "model.layers.2.self_attn.q_norm": false,
540
+ "model.layers.2.self_attn.k_norm": false,
541
+ "model.layers.2.self_attn.rope": false,
542
+ "model.layers.2.mlp.gate_proj": true,
543
+ "model.layers.2.mlp.down_proj": true,
544
+ "model.layers.2.mlp.up_proj": true,
545
+ "model.layers.2.input_layernorm": false,
546
+ "model.layers.2.post_attention_layernorm": false,
547
+ "model.layers.3.self_attn.q_proj": true,
548
+ "model.layers.3.self_attn.k_proj": true,
549
+ "model.layers.3.self_attn.v_proj": true,
550
+ "model.layers.3.self_attn.o_proj": true,
551
+ "model.layers.3.self_attn.q_norm": false,
552
+ "model.layers.3.self_attn.k_norm": false,
553
+ "model.layers.3.self_attn.rope": false,
554
+ "model.layers.3.mlp.gate_proj": true,
555
+ "model.layers.3.mlp.down_proj": true,
556
+ "model.layers.3.mlp.up_proj": true,
557
+ "model.layers.3.input_layernorm": false,
558
+ "model.layers.3.post_attention_layernorm": false,
559
+ "model.layers.4.self_attn.q_proj": true,
560
+ "model.layers.4.self_attn.k_proj": true,
561
+ "model.layers.4.self_attn.v_proj": true,
562
+ "model.layers.4.self_attn.o_proj": true,
563
+ "model.layers.4.self_attn.q_norm": false,
564
+ "model.layers.4.self_attn.k_norm": false,
565
+ "model.layers.4.self_attn.rope": false,
566
+ "model.layers.4.mlp.gate_proj": true,
567
+ "model.layers.4.mlp.down_proj": true,
568
+ "model.layers.4.mlp.up_proj": true,
569
+ "model.layers.4.input_layernorm": false,
570
+ "model.layers.4.post_attention_layernorm": false,
571
+ "model.layers.5.self_attn.q_proj": true,
572
+ "model.layers.5.self_attn.k_proj": true,
573
+ "model.layers.5.self_attn.v_proj": true,
574
+ "model.layers.5.self_attn.o_proj": true,
575
+ "model.layers.5.self_attn.q_norm": false,
576
+ "model.layers.5.self_attn.k_norm": false,
577
+ "model.layers.5.self_attn.rope": false,
578
+ "model.layers.5.mlp.gate_proj": true,
579
+ "model.layers.5.mlp.down_proj": true,
580
+ "model.layers.5.mlp.up_proj": true,
581
+ "model.layers.5.input_layernorm": false,
582
+ "model.layers.5.post_attention_layernorm": false,
583
+ "model.layers.6.self_attn.q_proj": true,
584
+ "model.layers.6.self_attn.k_proj": true,
585
+ "model.layers.6.self_attn.v_proj": true,
586
+ "model.layers.6.self_attn.o_proj": true,
587
+ "model.layers.6.self_attn.q_norm": false,
588
+ "model.layers.6.self_attn.k_norm": false,
589
+ "model.layers.6.self_attn.rope": false,
590
+ "model.layers.6.mlp.gate_proj": true,
591
+ "model.layers.6.mlp.down_proj": true,
592
+ "model.layers.6.mlp.up_proj": true,
593
+ "model.layers.6.input_layernorm": false,
594
+ "model.layers.6.post_attention_layernorm": false,
595
+ "model.layers.7.self_attn.q_proj": true,
596
+ "model.layers.7.self_attn.k_proj": true,
597
+ "model.layers.7.self_attn.v_proj": true,
598
+ "model.layers.7.self_attn.o_proj": true,
599
+ "model.layers.7.self_attn.q_norm": false,
600
+ "model.layers.7.self_attn.k_norm": false,
601
+ "model.layers.7.self_attn.rope": false,
602
+ "model.layers.7.mlp.gate_proj": true,
603
+ "model.layers.7.mlp.down_proj": true,
604
+ "model.layers.7.mlp.up_proj": true,
605
+ "model.layers.7.input_layernorm": false,
606
+ "model.layers.7.post_attention_layernorm": false,
607
+ "model.layers.8.self_attn.q_proj": true,
608
+ "model.layers.8.self_attn.k_proj": true,
609
+ "model.layers.8.self_attn.v_proj": true,
610
+ "model.layers.8.self_attn.o_proj": true,
611
+ "model.layers.8.self_attn.q_norm": false,
612
+ "model.layers.8.self_attn.k_norm": false,
613
+ "model.layers.8.self_attn.rope": false,
614
+ "model.layers.8.mlp.gate_proj": true,
615
+ "model.layers.8.mlp.down_proj": true,
616
+ "model.layers.8.mlp.up_proj": true,
617
+ "model.layers.8.input_layernorm": false,
618
+ "model.layers.8.post_attention_layernorm": false,
619
+ "model.layers.9.self_attn.q_proj": true,
620
+ "model.layers.9.self_attn.k_proj": true,
621
+ "model.layers.9.self_attn.v_proj": true,
622
+ "model.layers.9.self_attn.o_proj": true,
623
+ "model.layers.9.self_attn.q_norm": false,
624
+ "model.layers.9.self_attn.k_norm": false,
625
+ "model.layers.9.self_attn.rope": false,
626
+ "model.layers.9.mlp.gate_proj": true,
627
+ "model.layers.9.mlp.down_proj": true,
628
+ "model.layers.9.mlp.up_proj": true,
629
+ "model.layers.9.input_layernorm": false,
630
+ "model.layers.9.post_attention_layernorm": false,
631
+ "model.layers.10.self_attn.q_proj": true,
632
+ "model.layers.10.self_attn.k_proj": true,
633
+ "model.layers.10.self_attn.v_proj": true,
634
+ "model.layers.10.self_attn.o_proj": true,
635
+ "model.layers.10.self_attn.q_norm": false,
636
+ "model.layers.10.self_attn.k_norm": false,
637
+ "model.layers.10.self_attn.rope": false,
638
+ "model.layers.10.mlp.gate_proj": true,
639
+ "model.layers.10.mlp.down_proj": true,
640
+ "model.layers.10.mlp.up_proj": true,
641
+ "model.layers.10.input_layernorm": false,
642
+ "model.layers.10.post_attention_layernorm": false,
643
+ "model.layers.11.self_attn.q_proj": true,
644
+ "model.layers.11.self_attn.k_proj": true,
645
+ "model.layers.11.self_attn.v_proj": true,
646
+ "model.layers.11.self_attn.o_proj": true,
647
+ "model.layers.11.self_attn.q_norm": false,
648
+ "model.layers.11.self_attn.k_norm": false,
649
+ "model.layers.11.self_attn.rope": false,
650
+ "model.layers.11.mlp.gate_proj": true,
651
+ "model.layers.11.mlp.down_proj": true,
652
+ "model.layers.11.mlp.up_proj": true,
653
+ "model.layers.11.input_layernorm": false,
654
+ "model.layers.11.post_attention_layernorm": false,
655
+ "model.layers.12.self_attn.q_proj": true,
656
+ "model.layers.12.self_attn.k_proj": true,
657
+ "model.layers.12.self_attn.v_proj": true,
658
+ "model.layers.12.self_attn.o_proj": true,
659
+ "model.layers.12.self_attn.q_norm": false,
660
+ "model.layers.12.self_attn.k_norm": false,
661
+ "model.layers.12.self_attn.rope": false,
662
+ "model.layers.12.mlp.gate_proj": true,
663
+ "model.layers.12.mlp.down_proj": true,
664
+ "model.layers.12.mlp.up_proj": true,
665
+ "model.layers.12.input_layernorm": false,
666
+ "model.layers.12.post_attention_layernorm": false,
667
+ "model.layers.13.self_attn.q_proj": true,
668
+ "model.layers.13.self_attn.k_proj": true,
669
+ "model.layers.13.self_attn.v_proj": true,
670
+ "model.layers.13.self_attn.o_proj": true,
671
+ "model.layers.13.self_attn.q_norm": false,
672
+ "model.layers.13.self_attn.k_norm": false,
673
+ "model.layers.13.self_attn.rope": false,
674
+ "model.layers.13.mlp.gate_proj": true,
675
+ "model.layers.13.mlp.down_proj": true,
676
+ "model.layers.13.mlp.up_proj": true,
677
+ "model.layers.13.input_layernorm": false,
678
+ "model.layers.13.post_attention_layernorm": false,
679
+ "model.layers.14.self_attn.q_proj": true,
680
+ "model.layers.14.self_attn.k_proj": true,
681
+ "model.layers.14.self_attn.v_proj": true,
682
+ "model.layers.14.self_attn.o_proj": true,
683
+ "model.layers.14.self_attn.q_norm": false,
684
+ "model.layers.14.self_attn.k_norm": false,
685
+ "model.layers.14.self_attn.rope": false,
686
+ "model.layers.14.mlp.gate_proj": true,
687
+ "model.layers.14.mlp.down_proj": true,
688
+ "model.layers.14.mlp.up_proj": true,
689
+ "model.layers.14.input_layernorm": false,
690
+ "model.layers.14.post_attention_layernorm": false,
691
+ "model.layers.15.self_attn.q_proj": true,
692
+ "model.layers.15.self_attn.k_proj": true,
693
+ "model.layers.15.self_attn.v_proj": true,
694
+ "model.layers.15.self_attn.o_proj": true,
695
+ "model.layers.15.self_attn.q_norm": false,
696
+ "model.layers.15.self_attn.k_norm": false,
697
+ "model.layers.15.self_attn.rope": false,
698
+ "model.layers.15.mlp.gate_proj": true,
699
+ "model.layers.15.mlp.down_proj": true,
700
+ "model.layers.15.mlp.up_proj": true,
701
+ "model.layers.15.input_layernorm": false,
702
+ "model.layers.15.post_attention_layernorm": false,
703
+ "model.layers.16.self_attn.q_proj": true,
704
+ "model.layers.16.self_attn.k_proj": true,
705
+ "model.layers.16.self_attn.v_proj": true,
706
+ "model.layers.16.self_attn.o_proj": true,
707
+ "model.layers.16.self_attn.q_norm": false,
708
+ "model.layers.16.self_attn.k_norm": false,
709
+ "model.layers.16.self_attn.rope": false,
710
+ "model.layers.16.mlp.gate_proj": true,
711
+ "model.layers.16.mlp.down_proj": true,
712
+ "model.layers.16.mlp.up_proj": true,
713
+ "model.layers.16.input_layernorm": false,
714
+ "model.layers.16.post_attention_layernorm": false,
715
+ "model.layers.17.self_attn.q_proj": true,
716
+ "model.layers.17.self_attn.k_proj": true,
717
+ "model.layers.17.self_attn.v_proj": true,
718
+ "model.layers.17.self_attn.o_proj": true,
719
+ "model.layers.17.self_attn.q_norm": false,
720
+ "model.layers.17.self_attn.k_norm": false,
721
+ "model.layers.17.self_attn.rope": false,
722
+ "model.layers.17.mlp.gate_proj": true,
723
+ "model.layers.17.mlp.down_proj": true,
724
+ "model.layers.17.mlp.up_proj": true,
725
+ "model.layers.17.input_layernorm": false,
726
+ "model.layers.17.post_attention_layernorm": false,
727
+ "model.layers.18.self_attn.q_proj": true,
728
+ "model.layers.18.self_attn.k_proj": true,
729
+ "model.layers.18.self_attn.v_proj": true,
730
+ "model.layers.18.self_attn.o_proj": true,
731
+ "model.layers.18.self_attn.q_norm": false,
732
+ "model.layers.18.self_attn.k_norm": false,
733
+ "model.layers.18.self_attn.rope": false,
734
+ "model.layers.18.mlp.gate_proj": true,
735
+ "model.layers.18.mlp.down_proj": true,
736
+ "model.layers.18.mlp.up_proj": true,
737
+ "model.layers.18.input_layernorm": false,
738
+ "model.layers.18.post_attention_layernorm": false,
739
+ "model.layers.19.self_attn.q_proj": true,
740
+ "model.layers.19.self_attn.k_proj": true,
741
+ "model.layers.19.self_attn.v_proj": true,
742
+ "model.layers.19.self_attn.o_proj": true,
743
+ "model.layers.19.self_attn.q_norm": false,
744
+ "model.layers.19.self_attn.k_norm": false,
745
+ "model.layers.19.self_attn.rope": false,
746
+ "model.layers.19.mlp.gate_proj": true,
747
+ "model.layers.19.mlp.down_proj": true,
748
+ "model.layers.19.mlp.up_proj": true,
749
+ "model.layers.19.input_layernorm": false,
750
+ "model.layers.19.post_attention_layernorm": false,
751
+ "model.layers.20.self_attn.q_proj": true,
752
+ "model.layers.20.self_attn.k_proj": true,
753
+ "model.layers.20.self_attn.v_proj": true,
754
+ "model.layers.20.self_attn.o_proj": true,
755
+ "model.layers.20.self_attn.q_norm": false,
756
+ "model.layers.20.self_attn.k_norm": false,
757
+ "model.layers.20.self_attn.rope": false,
758
+ "model.layers.20.mlp.gate_proj": true,
759
+ "model.layers.20.mlp.down_proj": true,
760
+ "model.layers.20.mlp.up_proj": true,
761
+ "model.layers.20.input_layernorm": false,
762
+ "model.layers.20.post_attention_layernorm": false,
763
+ "model.layers.21.self_attn.q_proj": true,
764
+ "model.layers.21.self_attn.k_proj": true,
765
+ "model.layers.21.self_attn.v_proj": true,
766
+ "model.layers.21.self_attn.o_proj": true,
767
+ "model.layers.21.self_attn.q_norm": false,
768
+ "model.layers.21.self_attn.k_norm": false,
769
+ "model.layers.21.self_attn.rope": false,
770
+ "model.layers.21.mlp.gate_proj": true,
771
+ "model.layers.21.mlp.down_proj": true,
772
+ "model.layers.21.mlp.up_proj": true,
773
+ "model.layers.21.input_layernorm": false,
774
+ "model.layers.21.post_attention_layernorm": false,
775
+ "model.layers.22.self_attn.q_proj": true,
776
+ "model.layers.22.self_attn.k_proj": true,
777
+ "model.layers.22.self_attn.v_proj": true,
778
+ "model.layers.22.self_attn.o_proj": true,
779
+ "model.layers.22.self_attn.q_norm": false,
780
+ "model.layers.22.self_attn.k_norm": false,
781
+ "model.layers.22.self_attn.rope": false,
782
+ "model.layers.22.mlp.gate_proj": true,
783
+ "model.layers.22.mlp.down_proj": true,
784
+ "model.layers.22.mlp.up_proj": true,
785
+ "model.layers.22.input_layernorm": false,
786
+ "model.layers.22.post_attention_layernorm": false,
787
+ "model.layers.23.self_attn.q_proj": true,
788
+ "model.layers.23.self_attn.k_proj": true,
789
+ "model.layers.23.self_attn.v_proj": true,
790
+ "model.layers.23.self_attn.o_proj": true,
791
+ "model.layers.23.self_attn.q_norm": false,
792
+ "model.layers.23.self_attn.k_norm": false,
793
+ "model.layers.23.self_attn.rope": false,
794
+ "model.layers.23.mlp.gate_proj": true,
795
+ "model.layers.23.mlp.down_proj": true,
796
+ "model.layers.23.mlp.up_proj": true,
797
+ "model.layers.23.input_layernorm": false,
798
+ "model.layers.23.post_attention_layernorm": false,
799
+ "model.layers.24.self_attn.q_proj": true,
800
+ "model.layers.24.self_attn.k_proj": true,
801
+ "model.layers.24.self_attn.v_proj": true,
802
+ "model.layers.24.self_attn.o_proj": true,
803
+ "model.layers.24.self_attn.q_norm": false,
804
+ "model.layers.24.self_attn.k_norm": false,
805
+ "model.layers.24.self_attn.rope": false,
806
+ "model.layers.24.mlp.gate_proj": true,
807
+ "model.layers.24.mlp.down_proj": true,
808
+ "model.layers.24.mlp.up_proj": true,
809
+ "model.layers.24.input_layernorm": false,
810
+ "model.layers.24.post_attention_layernorm": false,
811
+ "model.layers.25.self_attn.q_proj": true,
812
+ "model.layers.25.self_attn.k_proj": true,
813
+ "model.layers.25.self_attn.v_proj": true,
814
+ "model.layers.25.self_attn.o_proj": true,
815
+ "model.layers.25.self_attn.q_norm": false,
816
+ "model.layers.25.self_attn.k_norm": false,
817
+ "model.layers.25.self_attn.rope": false,
818
+ "model.layers.25.mlp.gate_proj": true,
819
+ "model.layers.25.mlp.down_proj": true,
820
+ "model.layers.25.mlp.up_proj": true,
821
+ "model.layers.25.input_layernorm": false,
822
+ "model.layers.25.post_attention_layernorm": false,
823
+ "model.layers.26.self_attn.q_proj": true,
824
+ "model.layers.26.self_attn.k_proj": true,
825
+ "model.layers.26.self_attn.v_proj": true,
826
+ "model.layers.26.self_attn.o_proj": true,
827
+ "model.layers.26.self_attn.q_norm": false,
828
+ "model.layers.26.self_attn.k_norm": false,
829
+ "model.layers.26.self_attn.rope": false,
830
+ "model.layers.26.mlp.gate_proj": true,
831
+ "model.layers.26.mlp.down_proj": true,
832
+ "model.layers.26.mlp.up_proj": true,
833
+ "model.layers.26.input_layernorm": false,
834
+ "model.layers.26.post_attention_layernorm": false,
835
+ "model.layers.27.self_attn.q_proj": true,
836
+ "model.layers.27.self_attn.k_proj": true,
837
+ "model.layers.27.self_attn.v_proj": true,
838
+ "model.layers.27.self_attn.o_proj": true,
839
+ "model.layers.27.self_attn.q_norm": false,
840
+ "model.layers.27.self_attn.k_norm": false,
841
+ "model.layers.27.self_attn.rope": false,
842
+ "model.layers.27.mlp.gate_proj": true,
843
+ "model.layers.27.mlp.down_proj": true,
844
+ "model.layers.27.mlp.up_proj": true,
845
+ "model.layers.27.input_layernorm": false,
846
+ "model.layers.27.post_attention_layernorm": false,
847
+ "model.layers.28.self_attn.q_proj": true,
848
+ "model.layers.28.self_attn.k_proj": true,
849
+ "model.layers.28.self_attn.v_proj": true,
850
+ "model.layers.28.self_attn.o_proj": true,
851
+ "model.layers.28.self_attn.q_norm": false,
852
+ "model.layers.28.self_attn.k_norm": false,
853
+ "model.layers.28.self_attn.rope": false,
854
+ "model.layers.28.mlp.gate_proj": true,
855
+ "model.layers.28.mlp.down_proj": true,
856
+ "model.layers.28.mlp.up_proj": true,
857
+ "model.layers.28.input_layernorm": false,
858
+ "model.layers.28.post_attention_layernorm": false,
859
+ "model.layers.29.self_attn.q_proj": true,
860
+ "model.layers.29.self_attn.k_proj": true,
861
+ "model.layers.29.self_attn.v_proj": true,
862
+ "model.layers.29.self_attn.o_proj": true,
863
+ "model.layers.29.self_attn.q_norm": false,
864
+ "model.layers.29.self_attn.k_norm": false,
865
+ "model.layers.29.self_attn.rope": false,
866
+ "model.layers.29.mlp.gate_proj": true,
867
+ "model.layers.29.mlp.down_proj": true,
868
+ "model.layers.29.mlp.up_proj": true,
869
+ "model.layers.29.input_layernorm": false,
870
+ "model.layers.29.post_attention_layernorm": false,
871
+ "model.layers.30.self_attn.q_proj": true,
872
+ "model.layers.30.self_attn.k_proj": true,
873
+ "model.layers.30.self_attn.v_proj": true,
874
+ "model.layers.30.self_attn.o_proj": true,
875
+ "model.layers.30.self_attn.q_norm": false,
876
+ "model.layers.30.self_attn.k_norm": false,
877
+ "model.layers.30.self_attn.rope": false,
878
+ "model.layers.30.mlp.gate_proj": true,
879
+ "model.layers.30.mlp.down_proj": true,
880
+ "model.layers.30.mlp.up_proj": true,
881
+ "model.layers.30.input_layernorm": false,
882
+ "model.layers.30.post_attention_layernorm": false,
883
+ "model.layers.31.self_attn.q_proj": true,
884
+ "model.layers.31.self_attn.k_proj": true,
885
+ "model.layers.31.self_attn.v_proj": true,
886
+ "model.layers.31.self_attn.o_proj": true,
887
+ "model.layers.31.self_attn.q_norm": false,
888
+ "model.layers.31.self_attn.k_norm": false,
889
+ "model.layers.31.self_attn.rope": false,
890
+ "model.layers.31.mlp.gate_proj": true,
891
+ "model.layers.31.mlp.down_proj": true,
892
+ "model.layers.31.mlp.up_proj": true,
893
+ "model.layers.31.input_layernorm": false,
894
+ "model.layers.31.post_attention_layernorm": false,
895
+ "model.layers.32.self_attn.q_proj": true,
896
+ "model.layers.32.self_attn.k_proj": true,
897
+ "model.layers.32.self_attn.v_proj": true,
898
+ "model.layers.32.self_attn.o_proj": true,
899
+ "model.layers.32.self_attn.q_norm": false,
900
+ "model.layers.32.self_attn.k_norm": false,
901
+ "model.layers.32.self_attn.rope": false,
902
+ "model.layers.32.mlp.gate_proj": true,
903
+ "model.layers.32.mlp.down_proj": true,
904
+ "model.layers.32.mlp.up_proj": true,
905
+ "model.layers.32.input_layernorm": false,
906
+ "model.layers.32.post_attention_layernorm": false,
907
+ "model.layers.33.self_attn.q_proj": true,
908
+ "model.layers.33.self_attn.k_proj": true,
909
+ "model.layers.33.self_attn.v_proj": true,
910
+ "model.layers.33.self_attn.o_proj": true,
911
+ "model.layers.33.self_attn.q_norm": false,
912
+ "model.layers.33.self_attn.k_norm": false,
913
+ "model.layers.33.self_attn.rope": false,
914
+ "model.layers.33.mlp.gate_proj": true,
915
+ "model.layers.33.mlp.down_proj": true,
916
+ "model.layers.33.mlp.up_proj": true,
917
+ "model.layers.33.input_layernorm": false,
918
+ "model.layers.33.post_attention_layernorm": false,
919
+ "model.layers.34.self_attn.q_proj": true,
920
+ "model.layers.34.self_attn.k_proj": true,
921
+ "model.layers.34.self_attn.v_proj": true,
922
+ "model.layers.34.self_attn.o_proj": true,
923
+ "model.layers.34.self_attn.q_norm": false,
924
+ "model.layers.34.self_attn.k_norm": false,
925
+ "model.layers.34.self_attn.rope": false,
926
+ "model.layers.34.mlp.gate_proj": true,
927
+ "model.layers.34.mlp.down_proj": true,
928
+ "model.layers.34.mlp.up_proj": true,
929
+ "model.layers.34.input_layernorm": false,
930
+ "model.layers.34.post_attention_layernorm": false,
931
+ "model.layers.35.self_attn.q_proj": true,
932
+ "model.layers.35.self_attn.k_proj": true,
933
+ "model.layers.35.self_attn.v_proj": true,
934
+ "model.layers.35.self_attn.o_proj": true,
935
+ "model.layers.35.self_attn.q_norm": false,
936
+ "model.layers.35.self_attn.k_norm": false,
937
+ "model.layers.35.self_attn.rope": false,
938
+ "model.layers.35.mlp.gate_proj": true,
939
+ "model.layers.35.mlp.down_proj": true,
940
+ "model.layers.35.mlp.up_proj": true,
941
+ "model.layers.35.input_layernorm": false,
942
+ "model.layers.35.post_attention_layernorm": false,
943
+ "model.layers.36.self_attn.q_proj": true,
944
+ "model.layers.36.self_attn.k_proj": true,
945
+ "model.layers.36.self_attn.v_proj": true,
946
+ "model.layers.36.self_attn.o_proj": true,
947
+ "model.layers.36.self_attn.q_norm": false,
948
+ "model.layers.36.self_attn.k_norm": false,
949
+ "model.layers.36.self_attn.rope": false,
950
+ "model.layers.36.mlp.gate_proj": true,
951
+ "model.layers.36.mlp.down_proj": true,
952
+ "model.layers.36.mlp.up_proj": true,
953
+ "model.layers.36.input_layernorm": false,
954
+ "model.layers.36.post_attention_layernorm": false,
955
+ "model.layers.37.self_attn.q_proj": true,
956
+ "model.layers.37.self_attn.k_proj": true,
957
+ "model.layers.37.self_attn.v_proj": true,
958
+ "model.layers.37.self_attn.o_proj": true,
959
+ "model.layers.37.self_attn.q_norm": false,
960
+ "model.layers.37.self_attn.k_norm": false,
961
+ "model.layers.37.self_attn.rope": false,
962
+ "model.layers.37.mlp.gate_proj": true,
963
+ "model.layers.37.mlp.down_proj": true,
964
+ "model.layers.37.mlp.up_proj": true,
965
+ "model.layers.37.input_layernorm": false,
966
+ "model.layers.37.post_attention_layernorm": false,
967
+ "model.layers.38.self_attn.q_proj": true,
968
+ "model.layers.38.self_attn.k_proj": true,
969
+ "model.layers.38.self_attn.v_proj": true,
970
+ "model.layers.38.self_attn.o_proj": true,
971
+ "model.layers.38.self_attn.q_norm": false,
972
+ "model.layers.38.self_attn.k_norm": false,
973
+ "model.layers.38.self_attn.rope": false,
974
+ "model.layers.38.mlp.gate_proj": true,
975
+ "model.layers.38.mlp.down_proj": true,
976
+ "model.layers.38.mlp.up_proj": true,
977
+ "model.layers.38.input_layernorm": false,
978
+ "model.layers.38.post_attention_layernorm": false,
979
+ "model.layers.39.self_attn.q_proj": true,
980
+ "model.layers.39.self_attn.k_proj": true,
981
+ "model.layers.39.self_attn.v_proj": true,
982
+ "model.layers.39.self_attn.o_proj": true,
983
+ "model.layers.39.self_attn.q_norm": false,
984
+ "model.layers.39.self_attn.k_norm": false,
985
+ "model.layers.39.self_attn.rope": false,
986
+ "model.layers.39.mlp.gate_proj": true,
987
+ "model.layers.39.mlp.down_proj": true,
988
+ "model.layers.39.mlp.up_proj": true,
989
+ "model.layers.39.input_layernorm": false,
990
+ "model.layers.39.post_attention_layernorm": false,
991
+ "model.norm": false,
992
+ "lm_head": true
993
+ },
994
+ "rms_norm_eps": 1e-06,
995
+ "rope_scaling": null,
996
+ "rope_theta": 1000000,
997
+ "sliding_window": null,
998
+ "tie_word_embeddings": false,
999
+ "torch_dtype": "bfloat16",
1000
+ "transformers_version": "4.52.4",
1001
+ "unsloth_fixed": true,
1002
+ "unsloth_version": "2025.6.1",
1003
+ "use_cache": true,
1004
+ "use_sliding_window": false,
1005
+ "vocab_size": 151936
1006
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 40960,
9
+ "pad_token_id": 151654,
10
+ "temperature": 0.6,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.52.4"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f617f386158e23c25da25ad3a18fafe1dab450acd763ad452cda5cbdf5d45f9b
3
+ size 5354381352
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae449f331c250484d8558bd5c4484c4e8aace3377a1c0428c70544b5bf10798b
3
+ size 2953517062
model.safetensors.index.json ADDED
@@ -0,0 +1,1015 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8307783680,
4
+ "total_parameters": 14768307200
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model-00002-of-00002.safetensors",
8
+ "lm_head.scales": "model-00002-of-00002.safetensors",
9
+ "lm_head.weight": "model-00002-of-00002.safetensors",
10
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
11
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
12
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
36
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
37
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
61
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
65
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
66
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
68
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
69
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
86
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
87
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
90
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
93
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
94
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
96
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
97
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
111
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
112
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
115
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
116
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
118
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
119
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
121
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
122
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
126
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
127
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
129
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
130
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
133
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
136
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
137
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
140
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
141
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
143
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
144
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
146
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
147
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
151
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
152
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
154
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
155
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
158
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
159
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
161
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
162
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
165
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
166
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
168
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
169
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
171
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
172
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
176
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
179
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
180
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
183
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
184
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
186
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
187
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
190
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
191
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
193
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
194
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
196
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
197
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
201
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
202
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
204
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
205
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
208
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
209
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
211
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
215
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
218
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
219
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
221
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
222
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
226
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
227
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
229
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
230
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
233
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
234
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
236
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
237
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
240
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
241
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
243
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
244
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
246
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
247
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
251
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
252
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
254
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
258
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
261
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
262
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
265
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
266
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
268
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
269
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
271
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
276
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
277
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
279
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
280
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
283
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
284
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
286
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
287
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
290
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
291
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
293
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
294
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
296
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
297
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
301
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
302
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
304
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
305
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
308
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
309
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
311
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
312
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
315
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
316
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
318
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
321
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
322
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
326
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
327
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
329
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
330
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
333
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
334
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
336
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
337
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
340
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
341
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
343
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
344
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
346
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
347
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
351
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
352
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
354
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
355
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
358
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
359
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
361
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
362
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
365
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
366
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
368
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
369
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
371
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
372
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
376
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
377
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
379
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
380
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
383
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
384
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
386
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
387
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
390
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
391
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
393
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
394
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
396
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
397
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
401
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
402
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
404
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
405
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
408
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
409
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
411
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
412
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
415
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
416
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
418
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
419
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
421
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
422
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
426
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
427
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
429
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
433
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
434
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
436
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
437
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
440
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
441
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
443
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
444
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
446
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
447
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
451
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
452
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
454
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
455
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
458
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
459
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
461
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
462
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
465
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
466
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
468
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
471
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
472
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
474
+ "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
476
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
477
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
478
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
479
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
480
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
482
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
483
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
484
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
486
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
487
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
489
+ "model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
490
+ "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
491
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
492
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
493
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
494
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
495
+ "model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
496
+ "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
497
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
498
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
499
+ "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
500
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
501
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
502
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
504
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
505
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
506
+ "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
507
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
508
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
509
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
510
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
511
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
512
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
513
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
514
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
515
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
516
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
517
+ "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
518
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
519
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
520
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
521
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
522
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
523
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
524
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
525
+ "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
526
+ "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
527
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
528
+ "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
529
+ "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
530
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
531
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
532
+ "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
533
+ "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
534
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
535
+ "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
536
+ "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
537
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
538
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
539
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
540
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
541
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
542
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
543
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
544
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
545
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
546
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
547
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
548
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
549
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
550
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
551
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
552
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
553
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
554
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
555
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
556
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
557
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
558
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
559
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
560
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
561
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
562
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
563
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
564
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
565
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
566
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
567
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
568
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
569
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
570
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
571
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
572
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
573
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
574
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
575
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
576
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
577
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
578
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
579
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
580
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
581
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
582
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
583
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
584
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
585
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
586
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
587
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
588
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
589
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
590
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
591
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
592
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
593
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
594
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
595
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
596
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
597
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
598
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
599
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
600
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
601
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
602
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
603
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
604
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
605
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
606
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
607
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
608
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
609
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
610
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
611
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
612
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
613
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
614
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
615
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
616
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
617
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
618
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
619
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
620
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
621
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
622
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
623
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
624
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
625
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
626
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
627
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
628
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
629
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
630
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
631
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
632
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
633
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
634
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
635
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
636
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
637
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
638
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
639
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
640
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
641
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
642
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
643
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
644
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
645
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
646
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
647
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
648
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
649
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
650
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
651
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
652
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
653
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
654
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
655
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
656
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
657
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
658
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
659
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
660
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
661
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
662
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
663
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
664
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
665
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
666
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
667
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
668
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
669
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
670
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
671
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
672
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
673
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
674
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
675
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
676
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
677
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
678
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
679
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
680
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
681
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
682
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
683
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
684
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
685
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
686
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
687
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
688
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
689
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
690
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
691
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
692
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
693
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
694
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
695
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
696
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
697
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
698
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
699
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
700
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
701
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
702
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
703
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
704
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
705
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
706
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
707
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
708
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
709
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
710
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
711
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
712
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
713
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
714
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
715
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
716
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
717
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
718
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
719
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
721
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
722
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
723
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
724
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
725
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
726
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
727
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
728
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
729
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
730
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
731
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
732
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
733
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
734
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
735
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
736
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
737
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
738
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
739
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
740
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
741
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
742
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
743
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
744
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
745
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
746
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
747
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
748
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
749
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
750
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
751
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
752
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
753
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
754
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
755
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
756
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
757
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
758
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
759
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
760
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
761
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
762
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
763
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
764
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
765
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
766
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
767
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
768
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
769
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
770
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
771
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
772
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
773
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
774
+ "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
775
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
776
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
777
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
778
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
779
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
780
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
781
+ "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
782
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
783
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
784
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
785
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
786
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
787
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
788
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
789
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
790
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
791
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
792
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
793
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
794
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
795
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
796
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
797
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
798
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
799
+ "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
800
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
801
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
802
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
803
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
804
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
805
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
806
+ "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
807
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
808
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
809
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
810
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
811
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
812
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
813
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
814
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
815
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
816
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
817
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
818
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
819
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
820
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
821
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
822
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
823
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
824
+ "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
825
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
826
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
827
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
828
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
829
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
830
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
831
+ "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
832
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
833
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
834
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
835
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
836
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
837
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
838
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
839
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
840
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
841
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
842
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
843
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
844
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
845
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
846
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
847
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
848
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
849
+ "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
850
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
851
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
852
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
853
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
854
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
855
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
856
+ "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
857
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
858
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
859
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
860
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
861
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
862
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
863
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
864
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
865
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
866
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
867
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
868
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
869
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
870
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
871
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
872
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
873
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
874
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
875
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
876
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
877
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
878
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
879
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
880
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
881
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
882
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
883
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
884
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
885
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
886
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
887
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
889
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
890
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
891
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
892
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
893
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
894
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
895
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
896
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
897
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
898
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
899
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
900
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
901
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
902
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
903
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
904
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
905
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
906
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
907
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
908
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
909
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
910
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
911
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
912
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
913
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
914
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
915
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
916
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
917
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
918
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
919
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
920
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
921
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
922
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
923
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
924
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
925
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
926
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
927
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
928
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
929
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
930
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
931
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
932
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
933
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
934
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
935
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
936
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
937
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
938
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
939
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
940
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
941
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
942
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
943
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
944
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
945
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
946
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
947
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
948
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
949
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
950
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
951
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
952
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
953
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
954
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
955
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
956
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
957
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
958
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
959
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
960
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
961
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
962
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
963
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
964
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
965
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
966
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
967
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
968
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
969
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
970
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
971
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
972
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
973
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
974
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
975
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
976
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
977
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
978
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
979
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
980
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
981
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
982
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
983
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
984
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
985
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
986
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
987
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
988
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
989
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
990
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
991
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
992
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
993
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
994
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
995
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
996
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
997
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
998
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
999
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1000
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1001
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1002
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1003
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1004
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1005
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1006
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1007
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1008
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1009
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1010
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1011
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1012
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1013
+ "model.norm.weight": "model-00002-of-00002.safetensors"
1014
+ }
1015
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 40960,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff