Hugging Face's logo

nightmedia
/
Qwen3-8B-YOYO-V2-Hybrid-qx64-hi-mlx

Text Generation
MLX
Safetensors
English
Chinese
qwen3
Merge
conversational
6-bit
Model card Files
xet
Community
nightmedia commited on
Commit
5cdf74c
·
verified ·
1 Parent(s): 99ed8eb

Add files using upload-large-folder tool

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +40 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +97 -0
  5. config.json +2070 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +915 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +240 -0
  13. 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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ base_model: YOYO-AI/Qwen3-8B-YOYO-V2-Hybrid
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - merge
10
+ - mlx
11
+ library_name: mlx
12
+ ---
13
+
14
+ # Qwen3-8B-YOYO-V2-Hybrid-qx64-hi-mlx
15
+
16
+ This model [Qwen3-8B-YOYO-V2-Hybrid-qx64-hi-mlx](https://huggingface.co/Qwen3-8B-YOYO-V2-Hybrid-qx64-hi-mlx) was
17
+ converted to MLX format from [YOYO-AI/Qwen3-8B-YOYO-V2-Hybrid](https://huggingface.co/YOYO-AI/Qwen3-8B-YOYO-V2-Hybrid)
18
+ using mlx-lm version **0.26.4**.
19
+
20
+ ## Use with mlx
21
+
22
+ ```bash
23
+ pip install mlx-lm
24
+ ```
25
+
26
+ ```python
27
+ from mlx_lm import load, generate
28
+
29
+ model, tokenizer = load("Qwen3-8B-YOYO-V2-Hybrid-qx64-hi-mlx")
30
+
31
+ prompt = "hello"
32
+
33
+ if tokenizer.chat_template is not None:
34
+ messages = [{"role": "user", "content": prompt}]
35
+ prompt = tokenizer.apply_chat_template(
36
+ messages, add_generation_prompt=True
37
+ )
38
+
39
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
40
+ ```
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 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 tool_start = '<tool_response>' %}
22
+ {%- set tool_start_length = tool_start|length %}
23
+ {%- set start_of_message = message.content[:tool_start_length] %}
24
+ {%- set tool_end = '</tool_response>' %}
25
+ {%- set tool_end_length = tool_end|length %}
26
+ {%- set start_pos = (message.content|length) - tool_end_length %}
27
+ {%- if start_pos < 0 %}
28
+ {%- set start_pos = 0 %}
29
+ {%- endif %}
30
+ {%- set end_of_message = message.content[start_pos:] %}
31
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
32
+ {%- set ns.multi_step_tool = false %}
33
+ {%- set ns.last_query_index = index %}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- for message in messages %}
37
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
38
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
39
+ {%- elif message.role == "assistant" %}
40
+ {%- set content = message.content %}
41
+ {%- set reasoning_content = '' %}
42
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
43
+ {%- set reasoning_content = message.reasoning_content %}
44
+ {%- else %}
45
+ {%- if '</think>' in message.content %}
46
+ {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
47
+ {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
48
+ {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- if loop.index0 > ns.last_query_index %}
52
+ {%- if loop.last or (not loop.last and reasoning_content) %}
53
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
54
+ {%- else %}
55
+ {{- '<|im_start|>' + message.role + '\n' + content }}
56
+ {%- endif %}
57
+ {%- else %}
58
+ {{- '<|im_start|>' + message.role + '\n' + content }}
59
+ {%- endif %}
60
+ {%- if message.tool_calls %}
61
+ {%- for tool_call in message.tool_calls %}
62
+ {%- if (loop.first and content) or (not loop.first) %}
63
+ {{- '\n' }}
64
+ {%- endif %}
65
+ {%- if tool_call.function %}
66
+ {%- set tool_call = tool_call.function %}
67
+ {%- endif %}
68
+ {{- '<tool_call>\n{"name": "' }}
69
+ {{- tool_call.name }}
70
+ {{- '", "arguments": ' }}
71
+ {%- if tool_call.arguments is string %}
72
+ {{- tool_call.arguments }}
73
+ {%- else %}
74
+ {{- tool_call.arguments | tojson }}
75
+ {%- endif %}
76
+ {{- '}\n</tool_call>' }}
77
+ {%- endfor %}
78
+ {%- endif %}
79
+ {{- '<|im_end|>\n' }}
80
+ {%- elif message.role == "tool" %}
81
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
82
+ {{- '<|im_start|>user' }}
83
+ {%- endif %}
84
+ {{- '\n<tool_response>\n' }}
85
+ {{- message.content }}
86
+ {{- '\n</tool_response>' }}
87
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
88
+ {{- '<|im_end|>\n' }}
89
+ {%- endif %}
90
+ {%- endif %}
91
+ {%- endfor %}
92
+ {%- if add_generation_prompt %}
93
+ {{- '<|im_start|>assistant\n' }}
94
+ {%- if enable_thinking is defined and enable_thinking is false %}
95
+ {{- '<think>\n\n</think>\n\n' }}
96
+ {%- endif %}
97
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "quantization": {
21
+ "group_size": 32,
22
+ "bits": 6,
23
+ "model.embed_tokens": {
24
+ "group_size": 32,
25
+ "bits": 4
26
+ },
27
+ "model.layers.0.self_attn.q_proj": {
28
+ "group_size": 32,
29
+ "bits": 8
30
+ },
31
+ "model.layers.0.self_attn.k_proj": {
32
+ "group_size": 32,
33
+ "bits": 8
34
+ },
35
+ "model.layers.0.self_attn.v_proj": {
36
+ "group_size": 32,
37
+ "bits": 8
38
+ },
39
+ "model.layers.0.self_attn.o_proj": {
40
+ "group_size": 32,
41
+ "bits": 8
42
+ },
43
+ "model.layers.0.mlp.gate_proj": {
44
+ "group_size": 32,
45
+ "bits": 8
46
+ },
47
+ "model.layers.0.mlp.down_proj": {
48
+ "group_size": 32,
49
+ "bits": 8
50
+ },
51
+ "model.layers.0.mlp.up_proj": {
52
+ "group_size": 32,
53
+ "bits": 8
54
+ },
55
+ "model.layers.1.self_attn.q_proj": {
56
+ "group_size": 32,
57
+ "bits": 4
58
+ },
59
+ "model.layers.1.self_attn.k_proj": {
60
+ "group_size": 32,
61
+ "bits": 4
62
+ },
63
+ "model.layers.1.self_attn.v_proj": {
64
+ "group_size": 32,
65
+ "bits": 8
66
+ },
67
+ "model.layers.1.self_attn.o_proj": {
68
+ "group_size": 32,
69
+ "bits": 4
70
+ },
71
+ "model.layers.1.mlp.gate_proj": {
72
+ "group_size": 32,
73
+ "bits": 4
74
+ },
75
+ "model.layers.1.mlp.down_proj": {
76
+ "group_size": 32,
77
+ "bits": 6
78
+ },
79
+ "model.layers.1.mlp.up_proj": {
80
+ "group_size": 32,
81
+ "bits": 4
82
+ },
83
+ "model.layers.2.self_attn.q_proj": {
84
+ "group_size": 32,
85
+ "bits": 4
86
+ },
87
+ "model.layers.2.self_attn.k_proj": {
88
+ "group_size": 32,
89
+ "bits": 4
90
+ },
91
+ "model.layers.2.self_attn.v_proj": {
92
+ "group_size": 32,
93
+ "bits": 8
94
+ },
95
+ "model.layers.2.self_attn.o_proj": {
96
+ "group_size": 32,
97
+ "bits": 4
98
+ },
99
+ "model.layers.2.mlp.gate_proj": {
100
+ "group_size": 32,
101
+ "bits": 4
102
+ },
103
+ "model.layers.2.mlp.down_proj": {
104
+ "group_size": 32,
105
+ "bits": 6
106
+ },
107
+ "model.layers.2.mlp.up_proj": {
108
+ "group_size": 32,
109
+ "bits": 4
110
+ },
111
+ "model.layers.3.self_attn.q_proj": {
112
+ "group_size": 32,
113
+ "bits": 4
114
+ },
115
+ "model.layers.3.self_attn.k_proj": {
116
+ "group_size": 32,
117
+ "bits": 4
118
+ },
119
+ "model.layers.3.self_attn.v_proj": {
120
+ "group_size": 32,
121
+ "bits": 8
122
+ },
123
+ "model.layers.3.self_attn.o_proj": {
124
+ "group_size": 32,
125
+ "bits": 4
126
+ },
127
+ "model.layers.3.mlp.gate_proj": {
128
+ "group_size": 32,
129
+ "bits": 4
130
+ },
131
+ "model.layers.3.mlp.down_proj": {
132
+ "group_size": 32,
133
+ "bits": 6
134
+ },
135
+ "model.layers.3.mlp.up_proj": {
136
+ "group_size": 32,
137
+ "bits": 4
138
+ },
139
+ "model.layers.4.self_attn.q_proj": {
140
+ "group_size": 32,
141
+ "bits": 4
142
+ },
143
+ "model.layers.4.self_attn.k_proj": {
144
+ "group_size": 32,
145
+ "bits": 4
146
+ },
147
+ "model.layers.4.self_attn.v_proj": {
148
+ "group_size": 32,
149
+ "bits": 4
150
+ },
151
+ "model.layers.4.self_attn.o_proj": {
152
+ "group_size": 32,
153
+ "bits": 4
154
+ },
155
+ "model.layers.4.mlp.gate_proj": {
156
+ "group_size": 32,
157
+ "bits": 4
158
+ },
159
+ "model.layers.4.mlp.down_proj": {
160
+ "group_size": 32,
161
+ "bits": 4
162
+ },
163
+ "model.layers.4.mlp.up_proj": {
164
+ "group_size": 32,
165
+ "bits": 4
166
+ },
167
+ "model.layers.5.self_attn.q_proj": {
168
+ "group_size": 32,
169
+ "bits": 4
170
+ },
171
+ "model.layers.5.self_attn.k_proj": {
172
+ "group_size": 32,
173
+ "bits": 4
174
+ },
175
+ "model.layers.5.self_attn.v_proj": {
176
+ "group_size": 32,
177
+ "bits": 4
178
+ },
179
+ "model.layers.5.self_attn.o_proj": {
180
+ "group_size": 32,
181
+ "bits": 4
182
+ },
183
+ "model.layers.5.mlp.gate_proj": {
184
+ "group_size": 32,
185
+ "bits": 4
186
+ },
187
+ "model.layers.5.mlp.down_proj": {
188
+ "group_size": 32,
189
+ "bits": 4
190
+ },
191
+ "model.layers.5.mlp.up_proj": {
192
+ "group_size": 32,
193
+ "bits": 4
194
+ },
195
+ "model.layers.6.self_attn.q_proj": {
196
+ "group_size": 32,
197
+ "bits": 4
198
+ },
199
+ "model.layers.6.self_attn.k_proj": {
200
+ "group_size": 32,
201
+ "bits": 4
202
+ },
203
+ "model.layers.6.self_attn.v_proj": {
204
+ "group_size": 32,
205
+ "bits": 6
206
+ },
207
+ "model.layers.6.self_attn.o_proj": {
208
+ "group_size": 32,
209
+ "bits": 4
210
+ },
211
+ "model.layers.6.mlp.gate_proj": {
212
+ "group_size": 32,
213
+ "bits": 4
214
+ },
215
+ "model.layers.6.mlp.down_proj": {
216
+ "group_size": 32,
217
+ "bits": 6
218
+ },
219
+ "model.layers.6.mlp.up_proj": {
220
+ "group_size": 32,
221
+ "bits": 4
222
+ },
223
+ "model.layers.7.self_attn.q_proj": {
224
+ "group_size": 32,
225
+ "bits": 4
226
+ },
227
+ "model.layers.7.self_attn.k_proj": {
228
+ "group_size": 32,
229
+ "bits": 4
230
+ },
231
+ "model.layers.7.self_attn.v_proj": {
232
+ "group_size": 32,
233
+ "bits": 4
234
+ },
235
+ "model.layers.7.self_attn.o_proj": {
236
+ "group_size": 32,
237
+ "bits": 4
238
+ },
239
+ "model.layers.7.mlp.gate_proj": {
240
+ "group_size": 32,
241
+ "bits": 4
242
+ },
243
+ "model.layers.7.mlp.down_proj": {
244
+ "group_size": 32,
245
+ "bits": 4
246
+ },
247
+ "model.layers.7.mlp.up_proj": {
248
+ "group_size": 32,
249
+ "bits": 4
250
+ },
251
+ "model.layers.8.self_attn.q_proj": {
252
+ "group_size": 32,
253
+ "bits": 4
254
+ },
255
+ "model.layers.8.self_attn.k_proj": {
256
+ "group_size": 32,
257
+ "bits": 4
258
+ },
259
+ "model.layers.8.self_attn.v_proj": {
260
+ "group_size": 32,
261
+ "bits": 4
262
+ },
263
+ "model.layers.8.self_attn.o_proj": {
264
+ "group_size": 32,
265
+ "bits": 4
266
+ },
267
+ "model.layers.8.mlp.gate_proj": {
268
+ "group_size": 32,
269
+ "bits": 4
270
+ },
271
+ "model.layers.8.mlp.down_proj": {
272
+ "group_size": 32,
273
+ "bits": 4
274
+ },
275
+ "model.layers.8.mlp.up_proj": {
276
+ "group_size": 32,
277
+ "bits": 4
278
+ },
279
+ "model.layers.9.self_attn.q_proj": {
280
+ "group_size": 32,
281
+ "bits": 4
282
+ },
283
+ "model.layers.9.self_attn.k_proj": {
284
+ "group_size": 32,
285
+ "bits": 4
286
+ },
287
+ "model.layers.9.self_attn.v_proj": {
288
+ "group_size": 32,
289
+ "bits": 6
290
+ },
291
+ "model.layers.9.self_attn.o_proj": {
292
+ "group_size": 32,
293
+ "bits": 4
294
+ },
295
+ "model.layers.9.mlp.gate_proj": {
296
+ "group_size": 32,
297
+ "bits": 4
298
+ },
299
+ "model.layers.9.mlp.down_proj": {
300
+ "group_size": 32,
301
+ "bits": 6
302
+ },
303
+ "model.layers.9.mlp.up_proj": {
304
+ "group_size": 32,
305
+ "bits": 4
306
+ },
307
+ "model.layers.10.self_attn.q_proj": {
308
+ "group_size": 32,
309
+ "bits": 4
310
+ },
311
+ "model.layers.10.self_attn.k_proj": {
312
+ "group_size": 32,
313
+ "bits": 4
314
+ },
315
+ "model.layers.10.self_attn.v_proj": {
316
+ "group_size": 32,
317
+ "bits": 4
318
+ },
319
+ "model.layers.10.self_attn.o_proj": {
320
+ "group_size": 32,
321
+ "bits": 4
322
+ },
323
+ "model.layers.10.mlp.gate_proj": {
324
+ "group_size": 32,
325
+ "bits": 4
326
+ },
327
+ "model.layers.10.mlp.down_proj": {
328
+ "group_size": 32,
329
+ "bits": 4
330
+ },
331
+ "model.layers.10.mlp.up_proj": {
332
+ "group_size": 32,
333
+ "bits": 4
334
+ },
335
+ "model.layers.11.self_attn.q_proj": {
336
+ "group_size": 32,
337
+ "bits": 4
338
+ },
339
+ "model.layers.11.self_attn.k_proj": {
340
+ "group_size": 32,
341
+ "bits": 4
342
+ },
343
+ "model.layers.11.self_attn.v_proj": {
344
+ "group_size": 32,
345
+ "bits": 4
346
+ },
347
+ "model.layers.11.self_attn.o_proj": {
348
+ "group_size": 32,
349
+ "bits": 4
350
+ },
351
+ "model.layers.11.mlp.gate_proj": {
352
+ "group_size": 32,
353
+ "bits": 4
354
+ },
355
+ "model.layers.11.mlp.down_proj": {
356
+ "group_size": 32,
357
+ "bits": 4
358
+ },
359
+ "model.layers.11.mlp.up_proj": {
360
+ "group_size": 32,
361
+ "bits": 4
362
+ },
363
+ "model.layers.12.self_attn.q_proj": {
364
+ "group_size": 32,
365
+ "bits": 4
366
+ },
367
+ "model.layers.12.self_attn.k_proj": {
368
+ "group_size": 32,
369
+ "bits": 4
370
+ },
371
+ "model.layers.12.self_attn.v_proj": {
372
+ "group_size": 32,
373
+ "bits": 6
374
+ },
375
+ "model.layers.12.self_attn.o_proj": {
376
+ "group_size": 32,
377
+ "bits": 4
378
+ },
379
+ "model.layers.12.mlp.gate_proj": {
380
+ "group_size": 32,
381
+ "bits": 4
382
+ },
383
+ "model.layers.12.mlp.down_proj": {
384
+ "group_size": 32,
385
+ "bits": 6
386
+ },
387
+ "model.layers.12.mlp.up_proj": {
388
+ "group_size": 32,
389
+ "bits": 4
390
+ },
391
+ "model.layers.13.self_attn.q_proj": {
392
+ "group_size": 32,
393
+ "bits": 4
394
+ },
395
+ "model.layers.13.self_attn.k_proj": {
396
+ "group_size": 32,
397
+ "bits": 4
398
+ },
399
+ "model.layers.13.self_attn.v_proj": {
400
+ "group_size": 32,
401
+ "bits": 4
402
+ },
403
+ "model.layers.13.self_attn.o_proj": {
404
+ "group_size": 32,
405
+ "bits": 4
406
+ },
407
+ "model.layers.13.mlp.gate_proj": {
408
+ "group_size": 32,
409
+ "bits": 4
410
+ },
411
+ "model.layers.13.mlp.down_proj": {
412
+ "group_size": 32,
413
+ "bits": 4
414
+ },
415
+ "model.layers.13.mlp.up_proj": {
416
+ "group_size": 32,
417
+ "bits": 4
418
+ },
419
+ "model.layers.14.self_attn.q_proj": {
420
+ "group_size": 32,
421
+ "bits": 4
422
+ },
423
+ "model.layers.14.self_attn.k_proj": {
424
+ "group_size": 32,
425
+ "bits": 4
426
+ },
427
+ "model.layers.14.self_attn.v_proj": {
428
+ "group_size": 32,
429
+ "bits": 4
430
+ },
431
+ "model.layers.14.self_attn.o_proj": {
432
+ "group_size": 32,
433
+ "bits": 4
434
+ },
435
+ "model.layers.14.mlp.gate_proj": {
436
+ "group_size": 32,
437
+ "bits": 4
438
+ },
439
+ "model.layers.14.mlp.down_proj": {
440
+ "group_size": 32,
441
+ "bits": 4
442
+ },
443
+ "model.layers.14.mlp.up_proj": {
444
+ "group_size": 32,
445
+ "bits": 4
446
+ },
447
+ "model.layers.15.self_attn.q_proj": {
448
+ "group_size": 32,
449
+ "bits": 4
450
+ },
451
+ "model.layers.15.self_attn.k_proj": {
452
+ "group_size": 32,
453
+ "bits": 4
454
+ },
455
+ "model.layers.15.self_attn.v_proj": {
456
+ "group_size": 32,
457
+ "bits": 6
458
+ },
459
+ "model.layers.15.self_attn.o_proj": {
460
+ "group_size": 32,
461
+ "bits": 4
462
+ },
463
+ "model.layers.15.mlp.gate_proj": {
464
+ "group_size": 32,
465
+ "bits": 4
466
+ },
467
+ "model.layers.15.mlp.down_proj": {
468
+ "group_size": 32,
469
+ "bits": 6
470
+ },
471
+ "model.layers.15.mlp.up_proj": {
472
+ "group_size": 32,
473
+ "bits": 4
474
+ },
475
+ "model.layers.16.self_attn.q_proj": {
476
+ "group_size": 32,
477
+ "bits": 4
478
+ },
479
+ "model.layers.16.self_attn.k_proj": {
480
+ "group_size": 32,
481
+ "bits": 4
482
+ },
483
+ "model.layers.16.self_attn.v_proj": {
484
+ "group_size": 32,
485
+ "bits": 4
486
+ },
487
+ "model.layers.16.self_attn.o_proj": {
488
+ "group_size": 32,
489
+ "bits": 4
490
+ },
491
+ "model.layers.16.mlp.gate_proj": {
492
+ "group_size": 32,
493
+ "bits": 4
494
+ },
495
+ "model.layers.16.mlp.down_proj": {
496
+ "group_size": 32,
497
+ "bits": 4
498
+ },
499
+ "model.layers.16.mlp.up_proj": {
500
+ "group_size": 32,
501
+ "bits": 4
502
+ },
503
+ "model.layers.17.self_attn.q_proj": {
504
+ "group_size": 32,
505
+ "bits": 4
506
+ },
507
+ "model.layers.17.self_attn.k_proj": {
508
+ "group_size": 32,
509
+ "bits": 4
510
+ },
511
+ "model.layers.17.self_attn.v_proj": {
512
+ "group_size": 32,
513
+ "bits": 4
514
+ },
515
+ "model.layers.17.self_attn.o_proj": {
516
+ "group_size": 32,
517
+ "bits": 4
518
+ },
519
+ "model.layers.17.mlp.gate_proj": {
520
+ "group_size": 32,
521
+ "bits": 4
522
+ },
523
+ "model.layers.17.mlp.down_proj": {
524
+ "group_size": 32,
525
+ "bits": 4
526
+ },
527
+ "model.layers.17.mlp.up_proj": {
528
+ "group_size": 32,
529
+ "bits": 4
530
+ },
531
+ "model.layers.18.self_attn.q_proj": {
532
+ "group_size": 32,
533
+ "bits": 4
534
+ },
535
+ "model.layers.18.self_attn.k_proj": {
536
+ "group_size": 32,
537
+ "bits": 4
538
+ },
539
+ "model.layers.18.self_attn.v_proj": {
540
+ "group_size": 32,
541
+ "bits": 6
542
+ },
543
+ "model.layers.18.self_attn.o_proj": {
544
+ "group_size": 32,
545
+ "bits": 4
546
+ },
547
+ "model.layers.18.mlp.gate_proj": {
548
+ "group_size": 32,
549
+ "bits": 4
550
+ },
551
+ "model.layers.18.mlp.down_proj": {
552
+ "group_size": 32,
553
+ "bits": 6
554
+ },
555
+ "model.layers.18.mlp.up_proj": {
556
+ "group_size": 32,
557
+ "bits": 4
558
+ },
559
+ "model.layers.19.self_attn.q_proj": {
560
+ "group_size": 32,
561
+ "bits": 4
562
+ },
563
+ "model.layers.19.self_attn.k_proj": {
564
+ "group_size": 32,
565
+ "bits": 4
566
+ },
567
+ "model.layers.19.self_attn.v_proj": {
568
+ "group_size": 32,
569
+ "bits": 4
570
+ },
571
+ "model.layers.19.self_attn.o_proj": {
572
+ "group_size": 32,
573
+ "bits": 4
574
+ },
575
+ "model.layers.19.mlp.gate_proj": {
576
+ "group_size": 32,
577
+ "bits": 4
578
+ },
579
+ "model.layers.19.mlp.down_proj": {
580
+ "group_size": 32,
581
+ "bits": 4
582
+ },
583
+ "model.layers.19.mlp.up_proj": {
584
+ "group_size": 32,
585
+ "bits": 4
586
+ },
587
+ "model.layers.20.self_attn.q_proj": {
588
+ "group_size": 32,
589
+ "bits": 4
590
+ },
591
+ "model.layers.20.self_attn.k_proj": {
592
+ "group_size": 32,
593
+ "bits": 4
594
+ },
595
+ "model.layers.20.self_attn.v_proj": {
596
+ "group_size": 32,
597
+ "bits": 4
598
+ },
599
+ "model.layers.20.self_attn.o_proj": {
600
+ "group_size": 32,
601
+ "bits": 4
602
+ },
603
+ "model.layers.20.mlp.gate_proj": {
604
+ "group_size": 32,
605
+ "bits": 4
606
+ },
607
+ "model.layers.20.mlp.down_proj": {
608
+ "group_size": 32,
609
+ "bits": 4
610
+ },
611
+ "model.layers.20.mlp.up_proj": {
612
+ "group_size": 32,
613
+ "bits": 4
614
+ },
615
+ "model.layers.21.self_attn.q_proj": {
616
+ "group_size": 32,
617
+ "bits": 4
618
+ },
619
+ "model.layers.21.self_attn.k_proj": {
620
+ "group_size": 32,
621
+ "bits": 4
622
+ },
623
+ "model.layers.21.self_attn.v_proj": {
624
+ "group_size": 32,
625
+ "bits": 6
626
+ },
627
+ "model.layers.21.self_attn.o_proj": {
628
+ "group_size": 32,
629
+ "bits": 4
630
+ },
631
+ "model.layers.21.mlp.gate_proj": {
632
+ "group_size": 32,
633
+ "bits": 4
634
+ },
635
+ "model.layers.21.mlp.down_proj": {
636
+ "group_size": 32,
637
+ "bits": 6
638
+ },
639
+ "model.layers.21.mlp.up_proj": {
640
+ "group_size": 32,
641
+ "bits": 4
642
+ },
643
+ "model.layers.22.self_attn.q_proj": {
644
+ "group_size": 32,
645
+ "bits": 4
646
+ },
647
+ "model.layers.22.self_attn.k_proj": {
648
+ "group_size": 32,
649
+ "bits": 4
650
+ },
651
+ "model.layers.22.self_attn.v_proj": {
652
+ "group_size": 32,
653
+ "bits": 4
654
+ },
655
+ "model.layers.22.self_attn.o_proj": {
656
+ "group_size": 32,
657
+ "bits": 4
658
+ },
659
+ "model.layers.22.mlp.gate_proj": {
660
+ "group_size": 32,
661
+ "bits": 4
662
+ },
663
+ "model.layers.22.mlp.down_proj": {
664
+ "group_size": 32,
665
+ "bits": 4
666
+ },
667
+ "model.layers.22.mlp.up_proj": {
668
+ "group_size": 32,
669
+ "bits": 4
670
+ },
671
+ "model.layers.23.self_attn.q_proj": {
672
+ "group_size": 32,
673
+ "bits": 4
674
+ },
675
+ "model.layers.23.self_attn.k_proj": {
676
+ "group_size": 32,
677
+ "bits": 4
678
+ },
679
+ "model.layers.23.self_attn.v_proj": {
680
+ "group_size": 32,
681
+ "bits": 4
682
+ },
683
+ "model.layers.23.self_attn.o_proj": {
684
+ "group_size": 32,
685
+ "bits": 4
686
+ },
687
+ "model.layers.23.mlp.gate_proj": {
688
+ "group_size": 32,
689
+ "bits": 4
690
+ },
691
+ "model.layers.23.mlp.down_proj": {
692
+ "group_size": 32,
693
+ "bits": 4
694
+ },
695
+ "model.layers.23.mlp.up_proj": {
696
+ "group_size": 32,
697
+ "bits": 4
698
+ },
699
+ "model.layers.24.self_attn.q_proj": {
700
+ "group_size": 32,
701
+ "bits": 4
702
+ },
703
+ "model.layers.24.self_attn.k_proj": {
704
+ "group_size": 32,
705
+ "bits": 4
706
+ },
707
+ "model.layers.24.self_attn.v_proj": {
708
+ "group_size": 32,
709
+ "bits": 6
710
+ },
711
+ "model.layers.24.self_attn.o_proj": {
712
+ "group_size": 32,
713
+ "bits": 4
714
+ },
715
+ "model.layers.24.mlp.gate_proj": {
716
+ "group_size": 32,
717
+ "bits": 4
718
+ },
719
+ "model.layers.24.mlp.down_proj": {
720
+ "group_size": 32,
721
+ "bits": 6
722
+ },
723
+ "model.layers.24.mlp.up_proj": {
724
+ "group_size": 32,
725
+ "bits": 4
726
+ },
727
+ "model.layers.25.self_attn.q_proj": {
728
+ "group_size": 32,
729
+ "bits": 4
730
+ },
731
+ "model.layers.25.self_attn.k_proj": {
732
+ "group_size": 32,
733
+ "bits": 4
734
+ },
735
+ "model.layers.25.self_attn.v_proj": {
736
+ "group_size": 32,
737
+ "bits": 4
738
+ },
739
+ "model.layers.25.self_attn.o_proj": {
740
+ "group_size": 32,
741
+ "bits": 4
742
+ },
743
+ "model.layers.25.mlp.gate_proj": {
744
+ "group_size": 32,
745
+ "bits": 4
746
+ },
747
+ "model.layers.25.mlp.down_proj": {
748
+ "group_size": 32,
749
+ "bits": 4
750
+ },
751
+ "model.layers.25.mlp.up_proj": {
752
+ "group_size": 32,
753
+ "bits": 4
754
+ },
755
+ "model.layers.26.self_attn.q_proj": {
756
+ "group_size": 32,
757
+ "bits": 4
758
+ },
759
+ "model.layers.26.self_attn.k_proj": {
760
+ "group_size": 32,
761
+ "bits": 4
762
+ },
763
+ "model.layers.26.self_attn.v_proj": {
764
+ "group_size": 32,
765
+ "bits": 4
766
+ },
767
+ "model.layers.26.self_attn.o_proj": {
768
+ "group_size": 32,
769
+ "bits": 4
770
+ },
771
+ "model.layers.26.mlp.gate_proj": {
772
+ "group_size": 32,
773
+ "bits": 4
774
+ },
775
+ "model.layers.26.mlp.down_proj": {
776
+ "group_size": 32,
777
+ "bits": 4
778
+ },
779
+ "model.layers.26.mlp.up_proj": {
780
+ "group_size": 32,
781
+ "bits": 4
782
+ },
783
+ "model.layers.27.self_attn.q_proj": {
784
+ "group_size": 32,
785
+ "bits": 4
786
+ },
787
+ "model.layers.27.self_attn.k_proj": {
788
+ "group_size": 32,
789
+ "bits": 4
790
+ },
791
+ "model.layers.27.self_attn.v_proj": {
792
+ "group_size": 32,
793
+ "bits": 6
794
+ },
795
+ "model.layers.27.self_attn.o_proj": {
796
+ "group_size": 32,
797
+ "bits": 4
798
+ },
799
+ "model.layers.27.mlp.gate_proj": {
800
+ "group_size": 32,
801
+ "bits": 4
802
+ },
803
+ "model.layers.27.mlp.down_proj": {
804
+ "group_size": 32,
805
+ "bits": 6
806
+ },
807
+ "model.layers.27.mlp.up_proj": {
808
+ "group_size": 32,
809
+ "bits": 4
810
+ },
811
+ "model.layers.28.self_attn.q_proj": {
812
+ "group_size": 32,
813
+ "bits": 4
814
+ },
815
+ "model.layers.28.self_attn.k_proj": {
816
+ "group_size": 32,
817
+ "bits": 4
818
+ },
819
+ "model.layers.28.self_attn.v_proj": {
820
+ "group_size": 32,
821
+ "bits": 4
822
+ },
823
+ "model.layers.28.self_attn.o_proj": {
824
+ "group_size": 32,
825
+ "bits": 4
826
+ },
827
+ "model.layers.28.mlp.gate_proj": {
828
+ "group_size": 32,
829
+ "bits": 4
830
+ },
831
+ "model.layers.28.mlp.down_proj": {
832
+ "group_size": 32,
833
+ "bits": 4
834
+ },
835
+ "model.layers.28.mlp.up_proj": {
836
+ "group_size": 32,
837
+ "bits": 4
838
+ },
839
+ "model.layers.29.self_attn.q_proj": {
840
+ "group_size": 32,
841
+ "bits": 4
842
+ },
843
+ "model.layers.29.self_attn.k_proj": {
844
+ "group_size": 32,
845
+ "bits": 4
846
+ },
847
+ "model.layers.29.self_attn.v_proj": {
848
+ "group_size": 32,
849
+ "bits": 4
850
+ },
851
+ "model.layers.29.self_attn.o_proj": {
852
+ "group_size": 32,
853
+ "bits": 4
854
+ },
855
+ "model.layers.29.mlp.gate_proj": {
856
+ "group_size": 32,
857
+ "bits": 4
858
+ },
859
+ "model.layers.29.mlp.down_proj": {
860
+ "group_size": 32,
861
+ "bits": 4
862
+ },
863
+ "model.layers.29.mlp.up_proj": {
864
+ "group_size": 32,
865
+ "bits": 4
866
+ },
867
+ "model.layers.30.self_attn.q_proj": {
868
+ "group_size": 32,
869
+ "bits": 4
870
+ },
871
+ "model.layers.30.self_attn.k_proj": {
872
+ "group_size": 32,
873
+ "bits": 4
874
+ },
875
+ "model.layers.30.self_attn.v_proj": {
876
+ "group_size": 32,
877
+ "bits": 6
878
+ },
879
+ "model.layers.30.self_attn.o_proj": {
880
+ "group_size": 32,
881
+ "bits": 4
882
+ },
883
+ "model.layers.30.mlp.gate_proj": {
884
+ "group_size": 32,
885
+ "bits": 4
886
+ },
887
+ "model.layers.30.mlp.down_proj": {
888
+ "group_size": 32,
889
+ "bits": 6
890
+ },
891
+ "model.layers.30.mlp.up_proj": {
892
+ "group_size": 32,
893
+ "bits": 4
894
+ },
895
+ "model.layers.31.self_attn.q_proj": {
896
+ "group_size": 32,
897
+ "bits": 4
898
+ },
899
+ "model.layers.31.self_attn.k_proj": {
900
+ "group_size": 32,
901
+ "bits": 4
902
+ },
903
+ "model.layers.31.self_attn.v_proj": {
904
+ "group_size": 32,
905
+ "bits": 6
906
+ },
907
+ "model.layers.31.self_attn.o_proj": {
908
+ "group_size": 32,
909
+ "bits": 4
910
+ },
911
+ "model.layers.31.mlp.gate_proj": {
912
+ "group_size": 32,
913
+ "bits": 4
914
+ },
915
+ "model.layers.31.mlp.down_proj": {
916
+ "group_size": 32,
917
+ "bits": 6
918
+ },
919
+ "model.layers.31.mlp.up_proj": {
920
+ "group_size": 32,
921
+ "bits": 4
922
+ },
923
+ "model.layers.32.self_attn.q_proj": {
924
+ "group_size": 32,
925
+ "bits": 4
926
+ },
927
+ "model.layers.32.self_attn.k_proj": {
928
+ "group_size": 32,
929
+ "bits": 4
930
+ },
931
+ "model.layers.32.self_attn.v_proj": {
932
+ "group_size": 32,
933
+ "bits": 6
934
+ },
935
+ "model.layers.32.self_attn.o_proj": {
936
+ "group_size": 32,
937
+ "bits": 4
938
+ },
939
+ "model.layers.32.mlp.gate_proj": {
940
+ "group_size": 32,
941
+ "bits": 4
942
+ },
943
+ "model.layers.32.mlp.down_proj": {
944
+ "group_size": 32,
945
+ "bits": 6
946
+ },
947
+ "model.layers.32.mlp.up_proj": {
948
+ "group_size": 32,
949
+ "bits": 4
950
+ },
951
+ "model.layers.33.self_attn.q_proj": {
952
+ "group_size": 32,
953
+ "bits": 4
954
+ },
955
+ "model.layers.33.self_attn.k_proj": {
956
+ "group_size": 32,
957
+ "bits": 4
958
+ },
959
+ "model.layers.33.self_attn.v_proj": {
960
+ "group_size": 32,
961
+ "bits": 6
962
+ },
963
+ "model.layers.33.self_attn.o_proj": {
964
+ "group_size": 32,
965
+ "bits": 4
966
+ },
967
+ "model.layers.33.mlp.gate_proj": {
968
+ "group_size": 32,
969
+ "bits": 4
970
+ },
971
+ "model.layers.33.mlp.down_proj": {
972
+ "group_size": 32,
973
+ "bits": 6
974
+ },
975
+ "model.layers.33.mlp.up_proj": {
976
+ "group_size": 32,
977
+ "bits": 4
978
+ },
979
+ "model.layers.34.self_attn.q_proj": {
980
+ "group_size": 32,
981
+ "bits": 4
982
+ },
983
+ "model.layers.34.self_attn.k_proj": {
984
+ "group_size": 32,
985
+ "bits": 4
986
+ },
987
+ "model.layers.34.self_attn.v_proj": {
988
+ "group_size": 32,
989
+ "bits": 6
990
+ },
991
+ "model.layers.34.self_attn.o_proj": {
992
+ "group_size": 32,
993
+ "bits": 4
994
+ },
995
+ "model.layers.34.mlp.gate_proj": {
996
+ "group_size": 32,
997
+ "bits": 4
998
+ },
999
+ "model.layers.34.mlp.down_proj": {
1000
+ "group_size": 32,
1001
+ "bits": 6
1002
+ },
1003
+ "model.layers.34.mlp.up_proj": {
1004
+ "group_size": 32,
1005
+ "bits": 4
1006
+ },
1007
+ "model.layers.35.self_attn.q_proj": {
1008
+ "group_size": 32,
1009
+ "bits": 4
1010
+ },
1011
+ "model.layers.35.self_attn.k_proj": {
1012
+ "group_size": 32,
1013
+ "bits": 4
1014
+ },
1015
+ "model.layers.35.self_attn.v_proj": {
1016
+ "group_size": 32,
1017
+ "bits": 6
1018
+ },
1019
+ "model.layers.35.self_attn.o_proj": {
1020
+ "group_size": 32,
1021
+ "bits": 4
1022
+ },
1023
+ "model.layers.35.mlp.gate_proj": {
1024
+ "group_size": 32,
1025
+ "bits": 4
1026
+ },
1027
+ "model.layers.35.mlp.down_proj": {
1028
+ "group_size": 32,
1029
+ "bits": 6
1030
+ },
1031
+ "model.layers.35.mlp.up_proj": {
1032
+ "group_size": 32,
1033
+ "bits": 4
1034
+ },
1035
+ "lm_head": {
1036
+ "group_size": 32,
1037
+ "bits": 6
1038
+ }
1039
+ },
1040
+ "quantization_config": {
1041
+ "group_size": 32,
1042
+ "bits": 6,
1043
+ "model.embed_tokens": {
1044
+ "group_size": 32,
1045
+ "bits": 4
1046
+ },
1047
+ "model.layers.0.self_attn.q_proj": {
1048
+ "group_size": 32,
1049
+ "bits": 8
1050
+ },
1051
+ "model.layers.0.self_attn.k_proj": {
1052
+ "group_size": 32,
1053
+ "bits": 8
1054
+ },
1055
+ "model.layers.0.self_attn.v_proj": {
1056
+ "group_size": 32,
1057
+ "bits": 8
1058
+ },
1059
+ "model.layers.0.self_attn.o_proj": {
1060
+ "group_size": 32,
1061
+ "bits": 8
1062
+ },
1063
+ "model.layers.0.mlp.gate_proj": {
1064
+ "group_size": 32,
1065
+ "bits": 8
1066
+ },
1067
+ "model.layers.0.mlp.down_proj": {
1068
+ "group_size": 32,
1069
+ "bits": 8
1070
+ },
1071
+ "model.layers.0.mlp.up_proj": {
1072
+ "group_size": 32,
1073
+ "bits": 8
1074
+ },
1075
+ "model.layers.1.self_attn.q_proj": {
1076
+ "group_size": 32,
1077
+ "bits": 4
1078
+ },
1079
+ "model.layers.1.self_attn.k_proj": {
1080
+ "group_size": 32,
1081
+ "bits": 4
1082
+ },
1083
+ "model.layers.1.self_attn.v_proj": {
1084
+ "group_size": 32,
1085
+ "bits": 8
1086
+ },
1087
+ "model.layers.1.self_attn.o_proj": {
1088
+ "group_size": 32,
1089
+ "bits": 4
1090
+ },
1091
+ "model.layers.1.mlp.gate_proj": {
1092
+ "group_size": 32,
1093
+ "bits": 4
1094
+ },
1095
+ "model.layers.1.mlp.down_proj": {
1096
+ "group_size": 32,
1097
+ "bits": 6
1098
+ },
1099
+ "model.layers.1.mlp.up_proj": {
1100
+ "group_size": 32,
1101
+ "bits": 4
1102
+ },
1103
+ "model.layers.2.self_attn.q_proj": {
1104
+ "group_size": 32,
1105
+ "bits": 4
1106
+ },
1107
+ "model.layers.2.self_attn.k_proj": {
1108
+ "group_size": 32,
1109
+ "bits": 4
1110
+ },
1111
+ "model.layers.2.self_attn.v_proj": {
1112
+ "group_size": 32,
1113
+ "bits": 8
1114
+ },
1115
+ "model.layers.2.self_attn.o_proj": {
1116
+ "group_size": 32,
1117
+ "bits": 4
1118
+ },
1119
+ "model.layers.2.mlp.gate_proj": {
1120
+ "group_size": 32,
1121
+ "bits": 4
1122
+ },
1123
+ "model.layers.2.mlp.down_proj": {
1124
+ "group_size": 32,
1125
+ "bits": 6
1126
+ },
1127
+ "model.layers.2.mlp.up_proj": {
1128
+ "group_size": 32,
1129
+ "bits": 4
1130
+ },
1131
+ "model.layers.3.self_attn.q_proj": {
1132
+ "group_size": 32,
1133
+ "bits": 4
1134
+ },
1135
+ "model.layers.3.self_attn.k_proj": {
1136
+ "group_size": 32,
1137
+ "bits": 4
1138
+ },
1139
+ "model.layers.3.self_attn.v_proj": {
1140
+ "group_size": 32,
1141
+ "bits": 8
1142
+ },
1143
+ "model.layers.3.self_attn.o_proj": {
1144
+ "group_size": 32,
1145
+ "bits": 4
1146
+ },
1147
+ "model.layers.3.mlp.gate_proj": {
1148
+ "group_size": 32,
1149
+ "bits": 4
1150
+ },
1151
+ "model.layers.3.mlp.down_proj": {
1152
+ "group_size": 32,
1153
+ "bits": 6
1154
+ },
1155
+ "model.layers.3.mlp.up_proj": {
1156
+ "group_size": 32,
1157
+ "bits": 4
1158
+ },
1159
+ "model.layers.4.self_attn.q_proj": {
1160
+ "group_size": 32,
1161
+ "bits": 4
1162
+ },
1163
+ "model.layers.4.self_attn.k_proj": {
1164
+ "group_size": 32,
1165
+ "bits": 4
1166
+ },
1167
+ "model.layers.4.self_attn.v_proj": {
1168
+ "group_size": 32,
1169
+ "bits": 4
1170
+ },
1171
+ "model.layers.4.self_attn.o_proj": {
1172
+ "group_size": 32,
1173
+ "bits": 4
1174
+ },
1175
+ "model.layers.4.mlp.gate_proj": {
1176
+ "group_size": 32,
1177
+ "bits": 4
1178
+ },
1179
+ "model.layers.4.mlp.down_proj": {
1180
+ "group_size": 32,
1181
+ "bits": 4
1182
+ },
1183
+ "model.layers.4.mlp.up_proj": {
1184
+ "group_size": 32,
1185
+ "bits": 4
1186
+ },
1187
+ "model.layers.5.self_attn.q_proj": {
1188
+ "group_size": 32,
1189
+ "bits": 4
1190
+ },
1191
+ "model.layers.5.self_attn.k_proj": {
1192
+ "group_size": 32,
1193
+ "bits": 4
1194
+ },
1195
+ "model.layers.5.self_attn.v_proj": {
1196
+ "group_size": 32,
1197
+ "bits": 4
1198
+ },
1199
+ "model.layers.5.self_attn.o_proj": {
1200
+ "group_size": 32,
1201
+ "bits": 4
1202
+ },
1203
+ "model.layers.5.mlp.gate_proj": {
1204
+ "group_size": 32,
1205
+ "bits": 4
1206
+ },
1207
+ "model.layers.5.mlp.down_proj": {
1208
+ "group_size": 32,
1209
+ "bits": 4
1210
+ },
1211
+ "model.layers.5.mlp.up_proj": {
1212
+ "group_size": 32,
1213
+ "bits": 4
1214
+ },
1215
+ "model.layers.6.self_attn.q_proj": {
1216
+ "group_size": 32,
1217
+ "bits": 4
1218
+ },
1219
+ "model.layers.6.self_attn.k_proj": {
1220
+ "group_size": 32,
1221
+ "bits": 4
1222
+ },
1223
+ "model.layers.6.self_attn.v_proj": {
1224
+ "group_size": 32,
1225
+ "bits": 6
1226
+ },
1227
+ "model.layers.6.self_attn.o_proj": {
1228
+ "group_size": 32,
1229
+ "bits": 4
1230
+ },
1231
+ "model.layers.6.mlp.gate_proj": {
1232
+ "group_size": 32,
1233
+ "bits": 4
1234
+ },
1235
+ "model.layers.6.mlp.down_proj": {
1236
+ "group_size": 32,
1237
+ "bits": 6
1238
+ },
1239
+ "model.layers.6.mlp.up_proj": {
1240
+ "group_size": 32,
1241
+ "bits": 4
1242
+ },
1243
+ "model.layers.7.self_attn.q_proj": {
1244
+ "group_size": 32,
1245
+ "bits": 4
1246
+ },
1247
+ "model.layers.7.self_attn.k_proj": {
1248
+ "group_size": 32,
1249
+ "bits": 4
1250
+ },
1251
+ "model.layers.7.self_attn.v_proj": {
1252
+ "group_size": 32,
1253
+ "bits": 4
1254
+ },
1255
+ "model.layers.7.self_attn.o_proj": {
1256
+ "group_size": 32,
1257
+ "bits": 4
1258
+ },
1259
+ "model.layers.7.mlp.gate_proj": {
1260
+ "group_size": 32,
1261
+ "bits": 4
1262
+ },
1263
+ "model.layers.7.mlp.down_proj": {
1264
+ "group_size": 32,
1265
+ "bits": 4
1266
+ },
1267
+ "model.layers.7.mlp.up_proj": {
1268
+ "group_size": 32,
1269
+ "bits": 4
1270
+ },
1271
+ "model.layers.8.self_attn.q_proj": {
1272
+ "group_size": 32,
1273
+ "bits": 4
1274
+ },
1275
+ "model.layers.8.self_attn.k_proj": {
1276
+ "group_size": 32,
1277
+ "bits": 4
1278
+ },
1279
+ "model.layers.8.self_attn.v_proj": {
1280
+ "group_size": 32,
1281
+ "bits": 4
1282
+ },
1283
+ "model.layers.8.self_attn.o_proj": {
1284
+ "group_size": 32,
1285
+ "bits": 4
1286
+ },
1287
+ "model.layers.8.mlp.gate_proj": {
1288
+ "group_size": 32,
1289
+ "bits": 4
1290
+ },
1291
+ "model.layers.8.mlp.down_proj": {
1292
+ "group_size": 32,
1293
+ "bits": 4
1294
+ },
1295
+ "model.layers.8.mlp.up_proj": {
1296
+ "group_size": 32,
1297
+ "bits": 4
1298
+ },
1299
+ "model.layers.9.self_attn.q_proj": {
1300
+ "group_size": 32,
1301
+ "bits": 4
1302
+ },
1303
+ "model.layers.9.self_attn.k_proj": {
1304
+ "group_size": 32,
1305
+ "bits": 4
1306
+ },
1307
+ "model.layers.9.self_attn.v_proj": {
1308
+ "group_size": 32,
1309
+ "bits": 6
1310
+ },
1311
+ "model.layers.9.self_attn.o_proj": {
1312
+ "group_size": 32,
1313
+ "bits": 4
1314
+ },
1315
+ "model.layers.9.mlp.gate_proj": {
1316
+ "group_size": 32,
1317
+ "bits": 4
1318
+ },
1319
+ "model.layers.9.mlp.down_proj": {
1320
+ "group_size": 32,
1321
+ "bits": 6
1322
+ },
1323
+ "model.layers.9.mlp.up_proj": {
1324
+ "group_size": 32,
1325
+ "bits": 4
1326
+ },
1327
+ "model.layers.10.self_attn.q_proj": {
1328
+ "group_size": 32,
1329
+ "bits": 4
1330
+ },
1331
+ "model.layers.10.self_attn.k_proj": {
1332
+ "group_size": 32,
1333
+ "bits": 4
1334
+ },
1335
+ "model.layers.10.self_attn.v_proj": {
1336
+ "group_size": 32,
1337
+ "bits": 4
1338
+ },
1339
+ "model.layers.10.self_attn.o_proj": {
1340
+ "group_size": 32,
1341
+ "bits": 4
1342
+ },
1343
+ "model.layers.10.mlp.gate_proj": {
1344
+ "group_size": 32,
1345
+ "bits": 4
1346
+ },
1347
+ "model.layers.10.mlp.down_proj": {
1348
+ "group_size": 32,
1349
+ "bits": 4
1350
+ },
1351
+ "model.layers.10.mlp.up_proj": {
1352
+ "group_size": 32,
1353
+ "bits": 4
1354
+ },
1355
+ "model.layers.11.self_attn.q_proj": {
1356
+ "group_size": 32,
1357
+ "bits": 4
1358
+ },
1359
+ "model.layers.11.self_attn.k_proj": {
1360
+ "group_size": 32,
1361
+ "bits": 4
1362
+ },
1363
+ "model.layers.11.self_attn.v_proj": {
1364
+ "group_size": 32,
1365
+ "bits": 4
1366
+ },
1367
+ "model.layers.11.self_attn.o_proj": {
1368
+ "group_size": 32,
1369
+ "bits": 4
1370
+ },
1371
+ "model.layers.11.mlp.gate_proj": {
1372
+ "group_size": 32,
1373
+ "bits": 4
1374
+ },
1375
+ "model.layers.11.mlp.down_proj": {
1376
+ "group_size": 32,
1377
+ "bits": 4
1378
+ },
1379
+ "model.layers.11.mlp.up_proj": {
1380
+ "group_size": 32,
1381
+ "bits": 4
1382
+ },
1383
+ "model.layers.12.self_attn.q_proj": {
1384
+ "group_size": 32,
1385
+ "bits": 4
1386
+ },
1387
+ "model.layers.12.self_attn.k_proj": {
1388
+ "group_size": 32,
1389
+ "bits": 4
1390
+ },
1391
+ "model.layers.12.self_attn.v_proj": {
1392
+ "group_size": 32,
1393
+ "bits": 6
1394
+ },
1395
+ "model.layers.12.self_attn.o_proj": {
1396
+ "group_size": 32,
1397
+ "bits": 4
1398
+ },
1399
+ "model.layers.12.mlp.gate_proj": {
1400
+ "group_size": 32,
1401
+ "bits": 4
1402
+ },
1403
+ "model.layers.12.mlp.down_proj": {
1404
+ "group_size": 32,
1405
+ "bits": 6
1406
+ },
1407
+ "model.layers.12.mlp.up_proj": {
1408
+ "group_size": 32,
1409
+ "bits": 4
1410
+ },
1411
+ "model.layers.13.self_attn.q_proj": {
1412
+ "group_size": 32,
1413
+ "bits": 4
1414
+ },
1415
+ "model.layers.13.self_attn.k_proj": {
1416
+ "group_size": 32,
1417
+ "bits": 4
1418
+ },
1419
+ "model.layers.13.self_attn.v_proj": {
1420
+ "group_size": 32,
1421
+ "bits": 4
1422
+ },
1423
+ "model.layers.13.self_attn.o_proj": {
1424
+ "group_size": 32,
1425
+ "bits": 4
1426
+ },
1427
+ "model.layers.13.mlp.gate_proj": {
1428
+ "group_size": 32,
1429
+ "bits": 4
1430
+ },
1431
+ "model.layers.13.mlp.down_proj": {
1432
+ "group_size": 32,
1433
+ "bits": 4
1434
+ },
1435
+ "model.layers.13.mlp.up_proj": {
1436
+ "group_size": 32,
1437
+ "bits": 4
1438
+ },
1439
+ "model.layers.14.self_attn.q_proj": {
1440
+ "group_size": 32,
1441
+ "bits": 4
1442
+ },
1443
+ "model.layers.14.self_attn.k_proj": {
1444
+ "group_size": 32,
1445
+ "bits": 4
1446
+ },
1447
+ "model.layers.14.self_attn.v_proj": {
1448
+ "group_size": 32,
1449
+ "bits": 4
1450
+ },
1451
+ "model.layers.14.self_attn.o_proj": {
1452
+ "group_size": 32,
1453
+ "bits": 4
1454
+ },
1455
+ "model.layers.14.mlp.gate_proj": {
1456
+ "group_size": 32,
1457
+ "bits": 4
1458
+ },
1459
+ "model.layers.14.mlp.down_proj": {
1460
+ "group_size": 32,
1461
+ "bits": 4
1462
+ },
1463
+ "model.layers.14.mlp.up_proj": {
1464
+ "group_size": 32,
1465
+ "bits": 4
1466
+ },
1467
+ "model.layers.15.self_attn.q_proj": {
1468
+ "group_size": 32,
1469
+ "bits": 4
1470
+ },
1471
+ "model.layers.15.self_attn.k_proj": {
1472
+ "group_size": 32,
1473
+ "bits": 4
1474
+ },
1475
+ "model.layers.15.self_attn.v_proj": {
1476
+ "group_size": 32,
1477
+ "bits": 6
1478
+ },
1479
+ "model.layers.15.self_attn.o_proj": {
1480
+ "group_size": 32,
1481
+ "bits": 4
1482
+ },
1483
+ "model.layers.15.mlp.gate_proj": {
1484
+ "group_size": 32,
1485
+ "bits": 4
1486
+ },
1487
+ "model.layers.15.mlp.down_proj": {
1488
+ "group_size": 32,
1489
+ "bits": 6
1490
+ },
1491
+ "model.layers.15.mlp.up_proj": {
1492
+ "group_size": 32,
1493
+ "bits": 4
1494
+ },
1495
+ "model.layers.16.self_attn.q_proj": {
1496
+ "group_size": 32,
1497
+ "bits": 4
1498
+ },
1499
+ "model.layers.16.self_attn.k_proj": {
1500
+ "group_size": 32,
1501
+ "bits": 4
1502
+ },
1503
+ "model.layers.16.self_attn.v_proj": {
1504
+ "group_size": 32,
1505
+ "bits": 4
1506
+ },
1507
+ "model.layers.16.self_attn.o_proj": {
1508
+ "group_size": 32,
1509
+ "bits": 4
1510
+ },
1511
+ "model.layers.16.mlp.gate_proj": {
1512
+ "group_size": 32,
1513
+ "bits": 4
1514
+ },
1515
+ "model.layers.16.mlp.down_proj": {
1516
+ "group_size": 32,
1517
+ "bits": 4
1518
+ },
1519
+ "model.layers.16.mlp.up_proj": {
1520
+ "group_size": 32,
1521
+ "bits": 4
1522
+ },
1523
+ "model.layers.17.self_attn.q_proj": {
1524
+ "group_size": 32,
1525
+ "bits": 4
1526
+ },
1527
+ "model.layers.17.self_attn.k_proj": {
1528
+ "group_size": 32,
1529
+ "bits": 4
1530
+ },
1531
+ "model.layers.17.self_attn.v_proj": {
1532
+ "group_size": 32,
1533
+ "bits": 4
1534
+ },
1535
+ "model.layers.17.self_attn.o_proj": {
1536
+ "group_size": 32,
1537
+ "bits": 4
1538
+ },
1539
+ "model.layers.17.mlp.gate_proj": {
1540
+ "group_size": 32,
1541
+ "bits": 4
1542
+ },
1543
+ "model.layers.17.mlp.down_proj": {
1544
+ "group_size": 32,
1545
+ "bits": 4
1546
+ },
1547
+ "model.layers.17.mlp.up_proj": {
1548
+ "group_size": 32,
1549
+ "bits": 4
1550
+ },
1551
+ "model.layers.18.self_attn.q_proj": {
1552
+ "group_size": 32,
1553
+ "bits": 4
1554
+ },
1555
+ "model.layers.18.self_attn.k_proj": {
1556
+ "group_size": 32,
1557
+ "bits": 4
1558
+ },
1559
+ "model.layers.18.self_attn.v_proj": {
1560
+ "group_size": 32,
1561
+ "bits": 6
1562
+ },
1563
+ "model.layers.18.self_attn.o_proj": {
1564
+ "group_size": 32,
1565
+ "bits": 4
1566
+ },
1567
+ "model.layers.18.mlp.gate_proj": {
1568
+ "group_size": 32,
1569
+ "bits": 4
1570
+ },
1571
+ "model.layers.18.mlp.down_proj": {
1572
+ "group_size": 32,
1573
+ "bits": 6
1574
+ },
1575
+ "model.layers.18.mlp.up_proj": {
1576
+ "group_size": 32,
1577
+ "bits": 4
1578
+ },
1579
+ "model.layers.19.self_attn.q_proj": {
1580
+ "group_size": 32,
1581
+ "bits": 4
1582
+ },
1583
+ "model.layers.19.self_attn.k_proj": {
1584
+ "group_size": 32,
1585
+ "bits": 4
1586
+ },
1587
+ "model.layers.19.self_attn.v_proj": {
1588
+ "group_size": 32,
1589
+ "bits": 4
1590
+ },
1591
+ "model.layers.19.self_attn.o_proj": {
1592
+ "group_size": 32,
1593
+ "bits": 4
1594
+ },
1595
+ "model.layers.19.mlp.gate_proj": {
1596
+ "group_size": 32,
1597
+ "bits": 4
1598
+ },
1599
+ "model.layers.19.mlp.down_proj": {
1600
+ "group_size": 32,
1601
+ "bits": 4
1602
+ },
1603
+ "model.layers.19.mlp.up_proj": {
1604
+ "group_size": 32,
1605
+ "bits": 4
1606
+ },
1607
+ "model.layers.20.self_attn.q_proj": {
1608
+ "group_size": 32,
1609
+ "bits": 4
1610
+ },
1611
+ "model.layers.20.self_attn.k_proj": {
1612
+ "group_size": 32,
1613
+ "bits": 4
1614
+ },
1615
+ "model.layers.20.self_attn.v_proj": {
1616
+ "group_size": 32,
1617
+ "bits": 4
1618
+ },
1619
+ "model.layers.20.self_attn.o_proj": {
1620
+ "group_size": 32,
1621
+ "bits": 4
1622
+ },
1623
+ "model.layers.20.mlp.gate_proj": {
1624
+ "group_size": 32,
1625
+ "bits": 4
1626
+ },
1627
+ "model.layers.20.mlp.down_proj": {
1628
+ "group_size": 32,
1629
+ "bits": 4
1630
+ },
1631
+ "model.layers.20.mlp.up_proj": {
1632
+ "group_size": 32,
1633
+ "bits": 4
1634
+ },
1635
+ "model.layers.21.self_attn.q_proj": {
1636
+ "group_size": 32,
1637
+ "bits": 4
1638
+ },
1639
+ "model.layers.21.self_attn.k_proj": {
1640
+ "group_size": 32,
1641
+ "bits": 4
1642
+ },
1643
+ "model.layers.21.self_attn.v_proj": {
1644
+ "group_size": 32,
1645
+ "bits": 6
1646
+ },
1647
+ "model.layers.21.self_attn.o_proj": {
1648
+ "group_size": 32,
1649
+ "bits": 4
1650
+ },
1651
+ "model.layers.21.mlp.gate_proj": {
1652
+ "group_size": 32,
1653
+ "bits": 4
1654
+ },
1655
+ "model.layers.21.mlp.down_proj": {
1656
+ "group_size": 32,
1657
+ "bits": 6
1658
+ },
1659
+ "model.layers.21.mlp.up_proj": {
1660
+ "group_size": 32,
1661
+ "bits": 4
1662
+ },
1663
+ "model.layers.22.self_attn.q_proj": {
1664
+ "group_size": 32,
1665
+ "bits": 4
1666
+ },
1667
+ "model.layers.22.self_attn.k_proj": {
1668
+ "group_size": 32,
1669
+ "bits": 4
1670
+ },
1671
+ "model.layers.22.self_attn.v_proj": {
1672
+ "group_size": 32,
1673
+ "bits": 4
1674
+ },
1675
+ "model.layers.22.self_attn.o_proj": {
1676
+ "group_size": 32,
1677
+ "bits": 4
1678
+ },
1679
+ "model.layers.22.mlp.gate_proj": {
1680
+ "group_size": 32,
1681
+ "bits": 4
1682
+ },
1683
+ "model.layers.22.mlp.down_proj": {
1684
+ "group_size": 32,
1685
+ "bits": 4
1686
+ },
1687
+ "model.layers.22.mlp.up_proj": {
1688
+ "group_size": 32,
1689
+ "bits": 4
1690
+ },
1691
+ "model.layers.23.self_attn.q_proj": {
1692
+ "group_size": 32,
1693
+ "bits": 4
1694
+ },
1695
+ "model.layers.23.self_attn.k_proj": {
1696
+ "group_size": 32,
1697
+ "bits": 4
1698
+ },
1699
+ "model.layers.23.self_attn.v_proj": {
1700
+ "group_size": 32,
1701
+ "bits": 4
1702
+ },
1703
+ "model.layers.23.self_attn.o_proj": {
1704
+ "group_size": 32,
1705
+ "bits": 4
1706
+ },
1707
+ "model.layers.23.mlp.gate_proj": {
1708
+ "group_size": 32,
1709
+ "bits": 4
1710
+ },
1711
+ "model.layers.23.mlp.down_proj": {
1712
+ "group_size": 32,
1713
+ "bits": 4
1714
+ },
1715
+ "model.layers.23.mlp.up_proj": {
1716
+ "group_size": 32,
1717
+ "bits": 4
1718
+ },
1719
+ "model.layers.24.self_attn.q_proj": {
1720
+ "group_size": 32,
1721
+ "bits": 4
1722
+ },
1723
+ "model.layers.24.self_attn.k_proj": {
1724
+ "group_size": 32,
1725
+ "bits": 4
1726
+ },
1727
+ "model.layers.24.self_attn.v_proj": {
1728
+ "group_size": 32,
1729
+ "bits": 6
1730
+ },
1731
+ "model.layers.24.self_attn.o_proj": {
1732
+ "group_size": 32,
1733
+ "bits": 4
1734
+ },
1735
+ "model.layers.24.mlp.gate_proj": {
1736
+ "group_size": 32,
1737
+ "bits": 4
1738
+ },
1739
+ "model.layers.24.mlp.down_proj": {
1740
+ "group_size": 32,
1741
+ "bits": 6
1742
+ },
1743
+ "model.layers.24.mlp.up_proj": {
1744
+ "group_size": 32,
1745
+ "bits": 4
1746
+ },
1747
+ "model.layers.25.self_attn.q_proj": {
1748
+ "group_size": 32,
1749
+ "bits": 4
1750
+ },
1751
+ "model.layers.25.self_attn.k_proj": {
1752
+ "group_size": 32,
1753
+ "bits": 4
1754
+ },
1755
+ "model.layers.25.self_attn.v_proj": {
1756
+ "group_size": 32,
1757
+ "bits": 4
1758
+ },
1759
+ "model.layers.25.self_attn.o_proj": {
1760
+ "group_size": 32,
1761
+ "bits": 4
1762
+ },
1763
+ "model.layers.25.mlp.gate_proj": {
1764
+ "group_size": 32,
1765
+ "bits": 4
1766
+ },
1767
+ "model.layers.25.mlp.down_proj": {
1768
+ "group_size": 32,
1769
+ "bits": 4
1770
+ },
1771
+ "model.layers.25.mlp.up_proj": {
1772
+ "group_size": 32,
1773
+ "bits": 4
1774
+ },
1775
+ "model.layers.26.self_attn.q_proj": {
1776
+ "group_size": 32,
1777
+ "bits": 4
1778
+ },
1779
+ "model.layers.26.self_attn.k_proj": {
1780
+ "group_size": 32,
1781
+ "bits": 4
1782
+ },
1783
+ "model.layers.26.self_attn.v_proj": {
1784
+ "group_size": 32,
1785
+ "bits": 4
1786
+ },
1787
+ "model.layers.26.self_attn.o_proj": {
1788
+ "group_size": 32,
1789
+ "bits": 4
1790
+ },
1791
+ "model.layers.26.mlp.gate_proj": {
1792
+ "group_size": 32,
1793
+ "bits": 4
1794
+ },
1795
+ "model.layers.26.mlp.down_proj": {
1796
+ "group_size": 32,
1797
+ "bits": 4
1798
+ },
1799
+ "model.layers.26.mlp.up_proj": {
1800
+ "group_size": 32,
1801
+ "bits": 4
1802
+ },
1803
+ "model.layers.27.self_attn.q_proj": {
1804
+ "group_size": 32,
1805
+ "bits": 4
1806
+ },
1807
+ "model.layers.27.self_attn.k_proj": {
1808
+ "group_size": 32,
1809
+ "bits": 4
1810
+ },
1811
+ "model.layers.27.self_attn.v_proj": {
1812
+ "group_size": 32,
1813
+ "bits": 6
1814
+ },
1815
+ "model.layers.27.self_attn.o_proj": {
1816
+ "group_size": 32,
1817
+ "bits": 4
1818
+ },
1819
+ "model.layers.27.mlp.gate_proj": {
1820
+ "group_size": 32,
1821
+ "bits": 4
1822
+ },
1823
+ "model.layers.27.mlp.down_proj": {
1824
+ "group_size": 32,
1825
+ "bits": 6
1826
+ },
1827
+ "model.layers.27.mlp.up_proj": {
1828
+ "group_size": 32,
1829
+ "bits": 4
1830
+ },
1831
+ "model.layers.28.self_attn.q_proj": {
1832
+ "group_size": 32,
1833
+ "bits": 4
1834
+ },
1835
+ "model.layers.28.self_attn.k_proj": {
1836
+ "group_size": 32,
1837
+ "bits": 4
1838
+ },
1839
+ "model.layers.28.self_attn.v_proj": {
1840
+ "group_size": 32,
1841
+ "bits": 4
1842
+ },
1843
+ "model.layers.28.self_attn.o_proj": {
1844
+ "group_size": 32,
1845
+ "bits": 4
1846
+ },
1847
+ "model.layers.28.mlp.gate_proj": {
1848
+ "group_size": 32,
1849
+ "bits": 4
1850
+ },
1851
+ "model.layers.28.mlp.down_proj": {
1852
+ "group_size": 32,
1853
+ "bits": 4
1854
+ },
1855
+ "model.layers.28.mlp.up_proj": {
1856
+ "group_size": 32,
1857
+ "bits": 4
1858
+ },
1859
+ "model.layers.29.self_attn.q_proj": {
1860
+ "group_size": 32,
1861
+ "bits": 4
1862
+ },
1863
+ "model.layers.29.self_attn.k_proj": {
1864
+ "group_size": 32,
1865
+ "bits": 4
1866
+ },
1867
+ "model.layers.29.self_attn.v_proj": {
1868
+ "group_size": 32,
1869
+ "bits": 4
1870
+ },
1871
+ "model.layers.29.self_attn.o_proj": {
1872
+ "group_size": 32,
1873
+ "bits": 4
1874
+ },
1875
+ "model.layers.29.mlp.gate_proj": {
1876
+ "group_size": 32,
1877
+ "bits": 4
1878
+ },
1879
+ "model.layers.29.mlp.down_proj": {
1880
+ "group_size": 32,
1881
+ "bits": 4
1882
+ },
1883
+ "model.layers.29.mlp.up_proj": {
1884
+ "group_size": 32,
1885
+ "bits": 4
1886
+ },
1887
+ "model.layers.30.self_attn.q_proj": {
1888
+ "group_size": 32,
1889
+ "bits": 4
1890
+ },
1891
+ "model.layers.30.self_attn.k_proj": {
1892
+ "group_size": 32,
1893
+ "bits": 4
1894
+ },
1895
+ "model.layers.30.self_attn.v_proj": {
1896
+ "group_size": 32,
1897
+ "bits": 6
1898
+ },
1899
+ "model.layers.30.self_attn.o_proj": {
1900
+ "group_size": 32,
1901
+ "bits": 4
1902
+ },
1903
+ "model.layers.30.mlp.gate_proj": {
1904
+ "group_size": 32,
1905
+ "bits": 4
1906
+ },
1907
+ "model.layers.30.mlp.down_proj": {
1908
+ "group_size": 32,
1909
+ "bits": 6
1910
+ },
1911
+ "model.layers.30.mlp.up_proj": {
1912
+ "group_size": 32,
1913
+ "bits": 4
1914
+ },
1915
+ "model.layers.31.self_attn.q_proj": {
1916
+ "group_size": 32,
1917
+ "bits": 4
1918
+ },
1919
+ "model.layers.31.self_attn.k_proj": {
1920
+ "group_size": 32,
1921
+ "bits": 4
1922
+ },
1923
+ "model.layers.31.self_attn.v_proj": {
1924
+ "group_size": 32,
1925
+ "bits": 6
1926
+ },
1927
+ "model.layers.31.self_attn.o_proj": {
1928
+ "group_size": 32,
1929
+ "bits": 4
1930
+ },
1931
+ "model.layers.31.mlp.gate_proj": {
1932
+ "group_size": 32,
1933
+ "bits": 4
1934
+ },
1935
+ "model.layers.31.mlp.down_proj": {
1936
+ "group_size": 32,
1937
+ "bits": 6
1938
+ },
1939
+ "model.layers.31.mlp.up_proj": {
1940
+ "group_size": 32,
1941
+ "bits": 4
1942
+ },
1943
+ "model.layers.32.self_attn.q_proj": {
1944
+ "group_size": 32,
1945
+ "bits": 4
1946
+ },
1947
+ "model.layers.32.self_attn.k_proj": {
1948
+ "group_size": 32,
1949
+ "bits": 4
1950
+ },
1951
+ "model.layers.32.self_attn.v_proj": {
1952
+ "group_size": 32,
1953
+ "bits": 6
1954
+ },
1955
+ "model.layers.32.self_attn.o_proj": {
1956
+ "group_size": 32,
1957
+ "bits": 4
1958
+ },
1959
+ "model.layers.32.mlp.gate_proj": {
1960
+ "group_size": 32,
1961
+ "bits": 4
1962
+ },
1963
+ "model.layers.32.mlp.down_proj": {
1964
+ "group_size": 32,
1965
+ "bits": 6
1966
+ },
1967
+ "model.layers.32.mlp.up_proj": {
1968
+ "group_size": 32,
1969
+ "bits": 4
1970
+ },
1971
+ "model.layers.33.self_attn.q_proj": {
1972
+ "group_size": 32,
1973
+ "bits": 4
1974
+ },
1975
+ "model.layers.33.self_attn.k_proj": {
1976
+ "group_size": 32,
1977
+ "bits": 4
1978
+ },
1979
+ "model.layers.33.self_attn.v_proj": {
1980
+ "group_size": 32,
1981
+ "bits": 6
1982
+ },
1983
+ "model.layers.33.self_attn.o_proj": {
1984
+ "group_size": 32,
1985
+ "bits": 4
1986
+ },
1987
+ "model.layers.33.mlp.gate_proj": {
1988
+ "group_size": 32,
1989
+ "bits": 4
1990
+ },
1991
+ "model.layers.33.mlp.down_proj": {
1992
+ "group_size": 32,
1993
+ "bits": 6
1994
+ },
1995
+ "model.layers.33.mlp.up_proj": {
1996
+ "group_size": 32,
1997
+ "bits": 4
1998
+ },
1999
+ "model.layers.34.self_attn.q_proj": {
2000
+ "group_size": 32,
2001
+ "bits": 4
2002
+ },
2003
+ "model.layers.34.self_attn.k_proj": {
2004
+ "group_size": 32,
2005
+ "bits": 4
2006
+ },
2007
+ "model.layers.34.self_attn.v_proj": {
2008
+ "group_size": 32,
2009
+ "bits": 6
2010
+ },
2011
+ "model.layers.34.self_attn.o_proj": {
2012
+ "group_size": 32,
2013
+ "bits": 4
2014
+ },
2015
+ "model.layers.34.mlp.gate_proj": {
2016
+ "group_size": 32,
2017
+ "bits": 4
2018
+ },
2019
+ "model.layers.34.mlp.down_proj": {
2020
+ "group_size": 32,
2021
+ "bits": 6
2022
+ },
2023
+ "model.layers.34.mlp.up_proj": {
2024
+ "group_size": 32,
2025
+ "bits": 4
2026
+ },
2027
+ "model.layers.35.self_attn.q_proj": {
2028
+ "group_size": 32,
2029
+ "bits": 4
2030
+ },
2031
+ "model.layers.35.self_attn.k_proj": {
2032
+ "group_size": 32,
2033
+ "bits": 4
2034
+ },
2035
+ "model.layers.35.self_attn.v_proj": {
2036
+ "group_size": 32,
2037
+ "bits": 6
2038
+ },
2039
+ "model.layers.35.self_attn.o_proj": {
2040
+ "group_size": 32,
2041
+ "bits": 4
2042
+ },
2043
+ "model.layers.35.mlp.gate_proj": {
2044
+ "group_size": 32,
2045
+ "bits": 4
2046
+ },
2047
+ "model.layers.35.mlp.down_proj": {
2048
+ "group_size": 32,
2049
+ "bits": 6
2050
+ },
2051
+ "model.layers.35.mlp.up_proj": {
2052
+ "group_size": 32,
2053
+ "bits": 4
2054
+ },
2055
+ "lm_head": {
2056
+ "group_size": 32,
2057
+ "bits": 6
2058
+ }
2059
+ },
2060
+ "rms_norm_eps": 1e-06,
2061
+ "rope_scaling": null,
2062
+ "rope_theta": 1000000,
2063
+ "sliding_window": null,
2064
+ "tie_word_embeddings": false,
2065
+ "torch_dtype": "bfloat16",
2066
+ "transformers_version": "4.51.3",
2067
+ "use_cache": true,
2068
+ "use_sliding_window": false,
2069
+ "vocab_size": 151669
2070
+ }
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 sha256:35c836971bb487c94a0bfd4834a7e850a08d7ee07104d54c864cbc885cb1bfbc
3
+ size 5061447248
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168e07b0365e02acd07c0c8c0125d0b182e8cbf8f8c3341f6d2c04bc46d2bd62
3
+ size 543582000
model.safetensors.index.json ADDED
@@ -0,0 +1,915 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5604925440,
4
+ "total_parameters": 8188548096
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-00001-of-00002.safetensors",
489
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
490
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
491
+ "model.layers.26.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
496
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
497
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
498
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
514
+ "model.layers.27.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
515
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
516
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
517
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
518
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
519
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
520
+ "model.layers.27.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
521
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
522
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
523
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
524
+ "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
525
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
526
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
527
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
529
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
530
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
531
+ "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
532
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
533
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
534
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
535
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
536
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
537
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
538
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
539
+ "model.layers.28.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
540
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
541
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
542
+ "model.layers.28.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
543
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
544
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
545
+ "model.layers.28.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
546
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
547
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
548
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
549
+ "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
550
+ "model.layers.28.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
551
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
552
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
553
+ "model.layers.28.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
554
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
555
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
556
+ "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
557
+ "model.layers.28.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
558
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
559
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
560
+ "model.layers.28.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
561
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
562
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
564
+ "model.layers.29.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
565
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
566
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
567
+ "model.layers.29.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
568
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
569
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
570
+ "model.layers.29.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
571
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
572
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
573
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
574
+ "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
575
+ "model.layers.29.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
576
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
577
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
578
+ "model.layers.29.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
579
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
580
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
581
+ "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
582
+ "model.layers.29.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
583
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
584
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
585
+ "model.layers.29.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
586
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
587
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
614
+ "model.layers.30.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
615
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
616
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
617
+ "model.layers.30.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
618
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
619
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
620
+ "model.layers.30.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
621
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
622
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
624
+ "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
625
+ "model.layers.30.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
626
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
627
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
628
+ "model.layers.30.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
629
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
630
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
631
+ "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
632
+ "model.layers.30.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
633
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
634
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.layers.30.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
636
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
637
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
638
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
639
+ "model.layers.31.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
640
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
641
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
642
+ "model.layers.31.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
643
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
644
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
645
+ "model.layers.31.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
646
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
647
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
648
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
649
+ "model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
650
+ "model.layers.31.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
651
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
652
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
653
+ "model.layers.31.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
654
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
655
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
656
+ "model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
657
+ "model.layers.31.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
658
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
659
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
660
+ "model.layers.31.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
661
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
662
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
663
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
664
+ "model.layers.32.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
665
+ "model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
666
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
667
+ "model.layers.32.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
668
+ "model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
669
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
670
+ "model.layers.32.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
671
+ "model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
672
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
673
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
674
+ "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
675
+ "model.layers.32.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
676
+ "model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
677
+ "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
678
+ "model.layers.32.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
679
+ "model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
680
+ "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
681
+ "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
682
+ "model.layers.32.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
683
+ "model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
684
+ "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
685
+ "model.layers.32.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
686
+ "model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
687
+ "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
688
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
689
+ "model.layers.33.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
690
+ "model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
691
+ "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
692
+ "model.layers.33.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
693
+ "model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
694
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
695
+ "model.layers.33.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
696
+ "model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
697
+ "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
698
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
699
+ "model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
700
+ "model.layers.33.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
701
+ "model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
702
+ "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
703
+ "model.layers.33.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
704
+ "model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
705
+ "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
706
+ "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
707
+ "model.layers.33.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
708
+ "model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
709
+ "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "model.layers.33.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
711
+ "model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
712
+ "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
713
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
714
+ "model.layers.34.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
715
+ "model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
716
+ "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
717
+ "model.layers.34.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
718
+ "model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
719
+ "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
720
+ "model.layers.34.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
721
+ "model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
722
+ "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
723
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
724
+ "model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
725
+ "model.layers.34.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
726
+ "model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
727
+ "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
728
+ "model.layers.34.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
729
+ "model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
730
+ "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
731
+ "model.layers.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
732
+ "model.layers.34.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
733
+ "model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
734
+ "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
735
+ "model.layers.34.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
736
+ "model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
737
+ "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
738
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
739
+ "model.layers.35.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
740
+ "model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
741
+ "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
742
+ "model.layers.35.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
743
+ "model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
744
+ "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
745
+ "model.layers.35.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
746
+ "model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
747
+ "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
748
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
749
+ "model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
750
+ "model.layers.35.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
751
+ "model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
752
+ "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
753
+ "model.layers.35.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
754
+ "model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
755
+ "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
756
+ "model.layers.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
757
+ "model.layers.35.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
758
+ "model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
759
+ "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
760
+ "model.layers.35.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
761
+ "model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
762
+ "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
763
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
764
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
765
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
766
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
767
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
768
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
769
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
770
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
771
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
772
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
773
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
774
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
775
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
776
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
777
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
778
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
779
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
780
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
781
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
782
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
783
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
784
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
785
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
786
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
787
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
788
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
789
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
790
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
791
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
792
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
793
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
794
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
795
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
796
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
797
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
798
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
799
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
800
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
801
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
802
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
803
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
804
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
805
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
806
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
807
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
808
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
809
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
810
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
811
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
812
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
813
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
814
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
815
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
816
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
817
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
818
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
819
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
820
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
821
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
822
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
823
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
824
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
825
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
826
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
827
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
828
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
829
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
830
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
831
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
832
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
833
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
834
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
835
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
836
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
837
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
838
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
839
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
840
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
841
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
842
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
843
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
844
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
845
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
846
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
847
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
848
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
849
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
850
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
851
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
852
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
853
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
854
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
855
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
856
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
857
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
858
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
859
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
860
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
861
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
862
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
863
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
864
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
865
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
866
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
867
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
868
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
869
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
870
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
871
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
872
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
873
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
874
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
875
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
876
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
877
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
878
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
879
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
880
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
881
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
882
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
883
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
884
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
885
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
886
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
887
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
889
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
890
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
891
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
892
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
893
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
894
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
895
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
896
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
897
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
898
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
899
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
900
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
901
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
902
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
903
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
904
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
905
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
906
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
907
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
908
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
909
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
910
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
911
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
912
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
913
+ "model.norm.weight": "model-00001-of-00002.safetensors"
914
+ }
915
+ }
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": "left",
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