Hugging Face's logo

mlx-community
/
Qwen3-32B-3bit

MLX
Safetensors
qwen3
3bit
quantized
3-bit
Model card Files
xet
Community
KCh3dRi4n commited on
Commit
b3304de
·
verified ·
1 Parent(s): 3baff28

Upload 3-bit quantized Qwen3-32B model

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. README.md +45 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +89 -0
  5. config.json +1580 -0
  6. generation_config.json +13 -0
  7. merges.txt +0 -0
  8. model-00001-of-00003.safetensors +3 -0
  9. model-00002-of-00003.safetensors +3 -0
  10. model-00003-of-00003.safetensors +3 -0
  11. model.safetensors.index.json +0 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +239 -0
  15. 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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen3-32B
4
+ tags:
5
+ - mlx
6
+ - 3bit
7
+ - quantized
8
+ ---
9
+
10
+ # Qwen3-32B 3bit MLX
11
+
12
+ This model is a 3-bit quantized version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) using MLX.
13
+
14
+ ## Model Details
15
+ - **Quantization**: 3-bit
16
+ - **Framework**: MLX
17
+ - **Base Model**: Qwen/Qwen3-32B
18
+ - **Model Size**: ~12GB (3-bit quantized)
19
+
20
+ ## Usage
21
+
22
+ ```python
23
+ from mlx_lm import load, generate
24
+
25
+ model, tokenizer = load("mlx-community/Qwen3-32B-3bit")
26
+
27
+ prompt = "Hello, how are you?"
28
+ messages = [{"role": "user", "content": prompt}]
29
+ formatted_prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
30
+
31
+ response = generate(model, tokenizer, prompt=formatted_prompt, max_tokens=100)
32
+ print(response)
33
+ ```
34
+
35
+ ## Requirements
36
+ - Apple Silicon Mac (M1/M2/M3)
37
+ - macOS 13.0+
38
+ - Python 3.8+
39
+ - MLX and mlx-lm packages
40
+
41
+ ## Installation
42
+
43
+ ```bash
44
+ pip install mlx mlx-lm
45
+ ```
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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,1580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 25600,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 64,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 64,
19
+ "num_key_value_heads": 8,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 3,
23
+ "model.embed_tokens": true,
24
+ "model.layers.0.self_attn.q_proj": true,
25
+ "model.layers.0.self_attn.k_proj": true,
26
+ "model.layers.0.self_attn.v_proj": true,
27
+ "model.layers.0.self_attn.o_proj": true,
28
+ "model.layers.0.self_attn.q_norm": false,
29
+ "model.layers.0.self_attn.k_norm": false,
30
+ "model.layers.0.self_attn.rope": false,
31
+ "model.layers.0.mlp.gate_proj": true,
32
+ "model.layers.0.mlp.down_proj": true,
33
+ "model.layers.0.mlp.up_proj": true,
34
+ "model.layers.0.input_layernorm": false,
35
+ "model.layers.0.post_attention_layernorm": false,
36
+ "model.layers.1.self_attn.q_proj": true,
37
+ "model.layers.1.self_attn.k_proj": true,
38
+ "model.layers.1.self_attn.v_proj": true,
39
+ "model.layers.1.self_attn.o_proj": true,
40
+ "model.layers.1.self_attn.q_norm": false,
41
+ "model.layers.1.self_attn.k_norm": false,
42
+ "model.layers.1.self_attn.rope": false,
43
+ "model.layers.1.mlp.gate_proj": true,
44
+ "model.layers.1.mlp.down_proj": true,
45
+ "model.layers.1.mlp.up_proj": true,
46
+ "model.layers.1.input_layernorm": false,
47
+ "model.layers.1.post_attention_layernorm": false,
48
+ "model.layers.2.self_attn.q_proj": true,
49
+ "model.layers.2.self_attn.k_proj": true,
50
+ "model.layers.2.self_attn.v_proj": true,
51
+ "model.layers.2.self_attn.o_proj": true,
52
+ "model.layers.2.self_attn.q_norm": false,
53
+ "model.layers.2.self_attn.k_norm": false,
54
+ "model.layers.2.self_attn.rope": false,
55
+ "model.layers.2.mlp.gate_proj": true,
56
+ "model.layers.2.mlp.down_proj": true,
57
+ "model.layers.2.mlp.up_proj": true,
58
+ "model.layers.2.input_layernorm": false,
59
+ "model.layers.2.post_attention_layernorm": false,
60
+ "model.layers.3.self_attn.q_proj": true,
61
+ "model.layers.3.self_attn.k_proj": true,
62
+ "model.layers.3.self_attn.v_proj": true,
63
+ "model.layers.3.self_attn.o_proj": true,
64
+ "model.layers.3.self_attn.q_norm": false,
65
+ "model.layers.3.self_attn.k_norm": false,
66
+ "model.layers.3.self_attn.rope": false,
67
+ "model.layers.3.mlp.gate_proj": true,
68
+ "model.layers.3.mlp.down_proj": true,
69
+ "model.layers.3.mlp.up_proj": true,
70
+ "model.layers.3.input_layernorm": false,
71
+ "model.layers.3.post_attention_layernorm": false,
72
+ "model.layers.4.self_attn.q_proj": true,
73
+ "model.layers.4.self_attn.k_proj": true,
74
+ "model.layers.4.self_attn.v_proj": true,
75
+ "model.layers.4.self_attn.o_proj": true,
76
+ "model.layers.4.self_attn.q_norm": false,
77
+ "model.layers.4.self_attn.k_norm": false,
78
+ "model.layers.4.self_attn.rope": false,
79
+ "model.layers.4.mlp.gate_proj": true,
80
+ "model.layers.4.mlp.down_proj": true,
81
+ "model.layers.4.mlp.up_proj": true,
82
+ "model.layers.4.input_layernorm": false,
83
+ "model.layers.4.post_attention_layernorm": false,
84
+ "model.layers.5.self_attn.q_proj": true,
85
+ "model.layers.5.self_attn.k_proj": true,
86
+ "model.layers.5.self_attn.v_proj": true,
87
+ "model.layers.5.self_attn.o_proj": true,
88
+ "model.layers.5.self_attn.q_norm": false,
89
+ "model.layers.5.self_attn.k_norm": false,
90
+ "model.layers.5.self_attn.rope": false,
91
+ "model.layers.5.mlp.gate_proj": true,
92
+ "model.layers.5.mlp.down_proj": true,
93
+ "model.layers.5.mlp.up_proj": true,
94
+ "model.layers.5.input_layernorm": false,
95
+ "model.layers.5.post_attention_layernorm": false,
96
+ "model.layers.6.self_attn.q_proj": true,
97
+ "model.layers.6.self_attn.k_proj": true,
98
+ "model.layers.6.self_attn.v_proj": true,
99
+ "model.layers.6.self_attn.o_proj": true,
100
+ "model.layers.6.self_attn.q_norm": false,
101
+ "model.layers.6.self_attn.k_norm": false,
102
+ "model.layers.6.self_attn.rope": false,
103
+ "model.layers.6.mlp.gate_proj": true,
104
+ "model.layers.6.mlp.down_proj": true,
105
+ "model.layers.6.mlp.up_proj": true,
106
+ "model.layers.6.input_layernorm": false,
107
+ "model.layers.6.post_attention_layernorm": false,
108
+ "model.layers.7.self_attn.q_proj": true,
109
+ "model.layers.7.self_attn.k_proj": true,
110
+ "model.layers.7.self_attn.v_proj": true,
111
+ "model.layers.7.self_attn.o_proj": true,
112
+ "model.layers.7.self_attn.q_norm": false,
113
+ "model.layers.7.self_attn.k_norm": false,
114
+ "model.layers.7.self_attn.rope": false,
115
+ "model.layers.7.mlp.gate_proj": true,
116
+ "model.layers.7.mlp.down_proj": true,
117
+ "model.layers.7.mlp.up_proj": true,
118
+ "model.layers.7.input_layernorm": false,
119
+ "model.layers.7.post_attention_layernorm": false,
120
+ "model.layers.8.self_attn.q_proj": true,
121
+ "model.layers.8.self_attn.k_proj": true,
122
+ "model.layers.8.self_attn.v_proj": true,
123
+ "model.layers.8.self_attn.o_proj": true,
124
+ "model.layers.8.self_attn.q_norm": false,
125
+ "model.layers.8.self_attn.k_norm": false,
126
+ "model.layers.8.self_attn.rope": false,
127
+ "model.layers.8.mlp.gate_proj": true,
128
+ "model.layers.8.mlp.down_proj": true,
129
+ "model.layers.8.mlp.up_proj": true,
130
+ "model.layers.8.input_layernorm": false,
131
+ "model.layers.8.post_attention_layernorm": false,
132
+ "model.layers.9.self_attn.q_proj": true,
133
+ "model.layers.9.self_attn.k_proj": true,
134
+ "model.layers.9.self_attn.v_proj": true,
135
+ "model.layers.9.self_attn.o_proj": true,
136
+ "model.layers.9.self_attn.q_norm": false,
137
+ "model.layers.9.self_attn.k_norm": false,
138
+ "model.layers.9.self_attn.rope": false,
139
+ "model.layers.9.mlp.gate_proj": true,
140
+ "model.layers.9.mlp.down_proj": true,
141
+ "model.layers.9.mlp.up_proj": true,
142
+ "model.layers.9.input_layernorm": false,
143
+ "model.layers.9.post_attention_layernorm": false,
144
+ "model.layers.10.self_attn.q_proj": true,
145
+ "model.layers.10.self_attn.k_proj": true,
146
+ "model.layers.10.self_attn.v_proj": true,
147
+ "model.layers.10.self_attn.o_proj": true,
148
+ "model.layers.10.self_attn.q_norm": false,
149
+ "model.layers.10.self_attn.k_norm": false,
150
+ "model.layers.10.self_attn.rope": false,
151
+ "model.layers.10.mlp.gate_proj": true,
152
+ "model.layers.10.mlp.down_proj": true,
153
+ "model.layers.10.mlp.up_proj": true,
154
+ "model.layers.10.input_layernorm": false,
155
+ "model.layers.10.post_attention_layernorm": false,
156
+ "model.layers.11.self_attn.q_proj": true,
157
+ "model.layers.11.self_attn.k_proj": true,
158
+ "model.layers.11.self_attn.v_proj": true,
159
+ "model.layers.11.self_attn.o_proj": true,
160
+ "model.layers.11.self_attn.q_norm": false,
161
+ "model.layers.11.self_attn.k_norm": false,
162
+ "model.layers.11.self_attn.rope": false,
163
+ "model.layers.11.mlp.gate_proj": true,
164
+ "model.layers.11.mlp.down_proj": true,
165
+ "model.layers.11.mlp.up_proj": true,
166
+ "model.layers.11.input_layernorm": false,
167
+ "model.layers.11.post_attention_layernorm": false,
168
+ "model.layers.12.self_attn.q_proj": true,
169
+ "model.layers.12.self_attn.k_proj": true,
170
+ "model.layers.12.self_attn.v_proj": true,
171
+ "model.layers.12.self_attn.o_proj": true,
172
+ "model.layers.12.self_attn.q_norm": false,
173
+ "model.layers.12.self_attn.k_norm": false,
174
+ "model.layers.12.self_attn.rope": false,
175
+ "model.layers.12.mlp.gate_proj": true,
176
+ "model.layers.12.mlp.down_proj": true,
177
+ "model.layers.12.mlp.up_proj": true,
178
+ "model.layers.12.input_layernorm": false,
179
+ "model.layers.12.post_attention_layernorm": false,
180
+ "model.layers.13.self_attn.q_proj": true,
181
+ "model.layers.13.self_attn.k_proj": true,
182
+ "model.layers.13.self_attn.v_proj": true,
183
+ "model.layers.13.self_attn.o_proj": true,
184
+ "model.layers.13.self_attn.q_norm": false,
185
+ "model.layers.13.self_attn.k_norm": false,
186
+ "model.layers.13.self_attn.rope": false,
187
+ "model.layers.13.mlp.gate_proj": true,
188
+ "model.layers.13.mlp.down_proj": true,
189
+ "model.layers.13.mlp.up_proj": true,
190
+ "model.layers.13.input_layernorm": false,
191
+ "model.layers.13.post_attention_layernorm": false,
192
+ "model.layers.14.self_attn.q_proj": true,
193
+ "model.layers.14.self_attn.k_proj": true,
194
+ "model.layers.14.self_attn.v_proj": true,
195
+ "model.layers.14.self_attn.o_proj": true,
196
+ "model.layers.14.self_attn.q_norm": false,
197
+ "model.layers.14.self_attn.k_norm": false,
198
+ "model.layers.14.self_attn.rope": false,
199
+ "model.layers.14.mlp.gate_proj": true,
200
+ "model.layers.14.mlp.down_proj": true,
201
+ "model.layers.14.mlp.up_proj": true,
202
+ "model.layers.14.input_layernorm": false,
203
+ "model.layers.14.post_attention_layernorm": false,
204
+ "model.layers.15.self_attn.q_proj": true,
205
+ "model.layers.15.self_attn.k_proj": true,
206
+ "model.layers.15.self_attn.v_proj": true,
207
+ "model.layers.15.self_attn.o_proj": true,
208
+ "model.layers.15.self_attn.q_norm": false,
209
+ "model.layers.15.self_attn.k_norm": false,
210
+ "model.layers.15.self_attn.rope": false,
211
+ "model.layers.15.mlp.gate_proj": true,
212
+ "model.layers.15.mlp.down_proj": true,
213
+ "model.layers.15.mlp.up_proj": true,
214
+ "model.layers.15.input_layernorm": false,
215
+ "model.layers.15.post_attention_layernorm": false,
216
+ "model.layers.16.self_attn.q_proj": true,
217
+ "model.layers.16.self_attn.k_proj": true,
218
+ "model.layers.16.self_attn.v_proj": true,
219
+ "model.layers.16.self_attn.o_proj": true,
220
+ "model.layers.16.self_attn.q_norm": false,
221
+ "model.layers.16.self_attn.k_norm": false,
222
+ "model.layers.16.self_attn.rope": false,
223
+ "model.layers.16.mlp.gate_proj": true,
224
+ "model.layers.16.mlp.down_proj": true,
225
+ "model.layers.16.mlp.up_proj": true,
226
+ "model.layers.16.input_layernorm": false,
227
+ "model.layers.16.post_attention_layernorm": false,
228
+ "model.layers.17.self_attn.q_proj": true,
229
+ "model.layers.17.self_attn.k_proj": true,
230
+ "model.layers.17.self_attn.v_proj": true,
231
+ "model.layers.17.self_attn.o_proj": true,
232
+ "model.layers.17.self_attn.q_norm": false,
233
+ "model.layers.17.self_attn.k_norm": false,
234
+ "model.layers.17.self_attn.rope": false,
235
+ "model.layers.17.mlp.gate_proj": true,
236
+ "model.layers.17.mlp.down_proj": true,
237
+ "model.layers.17.mlp.up_proj": true,
238
+ "model.layers.17.input_layernorm": false,
239
+ "model.layers.17.post_attention_layernorm": false,
240
+ "model.layers.18.self_attn.q_proj": true,
241
+ "model.layers.18.self_attn.k_proj": true,
242
+ "model.layers.18.self_attn.v_proj": true,
243
+ "model.layers.18.self_attn.o_proj": true,
244
+ "model.layers.18.self_attn.q_norm": false,
245
+ "model.layers.18.self_attn.k_norm": false,
246
+ "model.layers.18.self_attn.rope": false,
247
+ "model.layers.18.mlp.gate_proj": true,
248
+ "model.layers.18.mlp.down_proj": true,
249
+ "model.layers.18.mlp.up_proj": true,
250
+ "model.layers.18.input_layernorm": false,
251
+ "model.layers.18.post_attention_layernorm": false,
252
+ "model.layers.19.self_attn.q_proj": true,
253
+ "model.layers.19.self_attn.k_proj": true,
254
+ "model.layers.19.self_attn.v_proj": true,
255
+ "model.layers.19.self_attn.o_proj": true,
256
+ "model.layers.19.self_attn.q_norm": false,
257
+ "model.layers.19.self_attn.k_norm": false,
258
+ "model.layers.19.self_attn.rope": false,
259
+ "model.layers.19.mlp.gate_proj": true,
260
+ "model.layers.19.mlp.down_proj": true,
261
+ "model.layers.19.mlp.up_proj": true,
262
+ "model.layers.19.input_layernorm": false,
263
+ "model.layers.19.post_attention_layernorm": false,
264
+ "model.layers.20.self_attn.q_proj": true,
265
+ "model.layers.20.self_attn.k_proj": true,
266
+ "model.layers.20.self_attn.v_proj": true,
267
+ "model.layers.20.self_attn.o_proj": true,
268
+ "model.layers.20.self_attn.q_norm": false,
269
+ "model.layers.20.self_attn.k_norm": false,
270
+ "model.layers.20.self_attn.rope": false,
271
+ "model.layers.20.mlp.gate_proj": true,
272
+ "model.layers.20.mlp.down_proj": true,
273
+ "model.layers.20.mlp.up_proj": true,
274
+ "model.layers.20.input_layernorm": false,
275
+ "model.layers.20.post_attention_layernorm": false,
276
+ "model.layers.21.self_attn.q_proj": true,
277
+ "model.layers.21.self_attn.k_proj": true,
278
+ "model.layers.21.self_attn.v_proj": true,
279
+ "model.layers.21.self_attn.o_proj": true,
280
+ "model.layers.21.self_attn.q_norm": false,
281
+ "model.layers.21.self_attn.k_norm": false,
282
+ "model.layers.21.self_attn.rope": false,
283
+ "model.layers.21.mlp.gate_proj": true,
284
+ "model.layers.21.mlp.down_proj": true,
285
+ "model.layers.21.mlp.up_proj": true,
286
+ "model.layers.21.input_layernorm": false,
287
+ "model.layers.21.post_attention_layernorm": false,
288
+ "model.layers.22.self_attn.q_proj": true,
289
+ "model.layers.22.self_attn.k_proj": true,
290
+ "model.layers.22.self_attn.v_proj": true,
291
+ "model.layers.22.self_attn.o_proj": true,
292
+ "model.layers.22.self_attn.q_norm": false,
293
+ "model.layers.22.self_attn.k_norm": false,
294
+ "model.layers.22.self_attn.rope": false,
295
+ "model.layers.22.mlp.gate_proj": true,
296
+ "model.layers.22.mlp.down_proj": true,
297
+ "model.layers.22.mlp.up_proj": true,
298
+ "model.layers.22.input_layernorm": false,
299
+ "model.layers.22.post_attention_layernorm": false,
300
+ "model.layers.23.self_attn.q_proj": true,
301
+ "model.layers.23.self_attn.k_proj": true,
302
+ "model.layers.23.self_attn.v_proj": true,
303
+ "model.layers.23.self_attn.o_proj": true,
304
+ "model.layers.23.self_attn.q_norm": false,
305
+ "model.layers.23.self_attn.k_norm": false,
306
+ "model.layers.23.self_attn.rope": false,
307
+ "model.layers.23.mlp.gate_proj": true,
308
+ "model.layers.23.mlp.down_proj": true,
309
+ "model.layers.23.mlp.up_proj": true,
310
+ "model.layers.23.input_layernorm": false,
311
+ "model.layers.23.post_attention_layernorm": false,
312
+ "model.layers.24.self_attn.q_proj": true,
313
+ "model.layers.24.self_attn.k_proj": true,
314
+ "model.layers.24.self_attn.v_proj": true,
315
+ "model.layers.24.self_attn.o_proj": true,
316
+ "model.layers.24.self_attn.q_norm": false,
317
+ "model.layers.24.self_attn.k_norm": false,
318
+ "model.layers.24.self_attn.rope": false,
319
+ "model.layers.24.mlp.gate_proj": true,
320
+ "model.layers.24.mlp.down_proj": true,
321
+ "model.layers.24.mlp.up_proj": true,
322
+ "model.layers.24.input_layernorm": false,
323
+ "model.layers.24.post_attention_layernorm": false,
324
+ "model.layers.25.self_attn.q_proj": true,
325
+ "model.layers.25.self_attn.k_proj": true,
326
+ "model.layers.25.self_attn.v_proj": true,
327
+ "model.layers.25.self_attn.o_proj": true,
328
+ "model.layers.25.self_attn.q_norm": false,
329
+ "model.layers.25.self_attn.k_norm": false,
330
+ "model.layers.25.self_attn.rope": false,
331
+ "model.layers.25.mlp.gate_proj": true,
332
+ "model.layers.25.mlp.down_proj": true,
333
+ "model.layers.25.mlp.up_proj": true,
334
+ "model.layers.25.input_layernorm": false,
335
+ "model.layers.25.post_attention_layernorm": false,
336
+ "model.layers.26.self_attn.q_proj": true,
337
+ "model.layers.26.self_attn.k_proj": true,
338
+ "model.layers.26.self_attn.v_proj": true,
339
+ "model.layers.26.self_attn.o_proj": true,
340
+ "model.layers.26.self_attn.q_norm": false,
341
+ "model.layers.26.self_attn.k_norm": false,
342
+ "model.layers.26.self_attn.rope": false,
343
+ "model.layers.26.mlp.gate_proj": true,
344
+ "model.layers.26.mlp.down_proj": true,
345
+ "model.layers.26.mlp.up_proj": true,
346
+ "model.layers.26.input_layernorm": false,
347
+ "model.layers.26.post_attention_layernorm": false,
348
+ "model.layers.27.self_attn.q_proj": true,
349
+ "model.layers.27.self_attn.k_proj": true,
350
+ "model.layers.27.self_attn.v_proj": true,
351
+ "model.layers.27.self_attn.o_proj": true,
352
+ "model.layers.27.self_attn.q_norm": false,
353
+ "model.layers.27.self_attn.k_norm": false,
354
+ "model.layers.27.self_attn.rope": false,
355
+ "model.layers.27.mlp.gate_proj": true,
356
+ "model.layers.27.mlp.down_proj": true,
357
+ "model.layers.27.mlp.up_proj": true,
358
+ "model.layers.27.input_layernorm": false,
359
+ "model.layers.27.post_attention_layernorm": false,
360
+ "model.layers.28.self_attn.q_proj": true,
361
+ "model.layers.28.self_attn.k_proj": true,
362
+ "model.layers.28.self_attn.v_proj": true,
363
+ "model.layers.28.self_attn.o_proj": true,
364
+ "model.layers.28.self_attn.q_norm": false,
365
+ "model.layers.28.self_attn.k_norm": false,
366
+ "model.layers.28.self_attn.rope": false,
367
+ "model.layers.28.mlp.gate_proj": true,
368
+ "model.layers.28.mlp.down_proj": true,
369
+ "model.layers.28.mlp.up_proj": true,
370
+ "model.layers.28.input_layernorm": false,
371
+ "model.layers.28.post_attention_layernorm": false,
372
+ "model.layers.29.self_attn.q_proj": true,
373
+ "model.layers.29.self_attn.k_proj": true,
374
+ "model.layers.29.self_attn.v_proj": true,
375
+ "model.layers.29.self_attn.o_proj": true,
376
+ "model.layers.29.self_attn.q_norm": false,
377
+ "model.layers.29.self_attn.k_norm": false,
378
+ "model.layers.29.self_attn.rope": false,
379
+ "model.layers.29.mlp.gate_proj": true,
380
+ "model.layers.29.mlp.down_proj": true,
381
+ "model.layers.29.mlp.up_proj": true,
382
+ "model.layers.29.input_layernorm": false,
383
+ "model.layers.29.post_attention_layernorm": false,
384
+ "model.layers.30.self_attn.q_proj": true,
385
+ "model.layers.30.self_attn.k_proj": true,
386
+ "model.layers.30.self_attn.v_proj": true,
387
+ "model.layers.30.self_attn.o_proj": true,
388
+ "model.layers.30.self_attn.q_norm": false,
389
+ "model.layers.30.self_attn.k_norm": false,
390
+ "model.layers.30.self_attn.rope": false,
391
+ "model.layers.30.mlp.gate_proj": true,
392
+ "model.layers.30.mlp.down_proj": true,
393
+ "model.layers.30.mlp.up_proj": true,
394
+ "model.layers.30.input_layernorm": false,
395
+ "model.layers.30.post_attention_layernorm": false,
396
+ "model.layers.31.self_attn.q_proj": true,
397
+ "model.layers.31.self_attn.k_proj": true,
398
+ "model.layers.31.self_attn.v_proj": true,
399
+ "model.layers.31.self_attn.o_proj": true,
400
+ "model.layers.31.self_attn.q_norm": false,
401
+ "model.layers.31.self_attn.k_norm": false,
402
+ "model.layers.31.self_attn.rope": false,
403
+ "model.layers.31.mlp.gate_proj": true,
404
+ "model.layers.31.mlp.down_proj": true,
405
+ "model.layers.31.mlp.up_proj": true,
406
+ "model.layers.31.input_layernorm": false,
407
+ "model.layers.31.post_attention_layernorm": false,
408
+ "model.layers.32.self_attn.q_proj": true,
409
+ "model.layers.32.self_attn.k_proj": true,
410
+ "model.layers.32.self_attn.v_proj": true,
411
+ "model.layers.32.self_attn.o_proj": true,
412
+ "model.layers.32.self_attn.q_norm": false,
413
+ "model.layers.32.self_attn.k_norm": false,
414
+ "model.layers.32.self_attn.rope": false,
415
+ "model.layers.32.mlp.gate_proj": true,
416
+ "model.layers.32.mlp.down_proj": true,
417
+ "model.layers.32.mlp.up_proj": true,
418
+ "model.layers.32.input_layernorm": false,
419
+ "model.layers.32.post_attention_layernorm": false,
420
+ "model.layers.33.self_attn.q_proj": true,
421
+ "model.layers.33.self_attn.k_proj": true,
422
+ "model.layers.33.self_attn.v_proj": true,
423
+ "model.layers.33.self_attn.o_proj": true,
424
+ "model.layers.33.self_attn.q_norm": false,
425
+ "model.layers.33.self_attn.k_norm": false,
426
+ "model.layers.33.self_attn.rope": false,
427
+ "model.layers.33.mlp.gate_proj": true,
428
+ "model.layers.33.mlp.down_proj": true,
429
+ "model.layers.33.mlp.up_proj": true,
430
+ "model.layers.33.input_layernorm": false,
431
+ "model.layers.33.post_attention_layernorm": false,
432
+ "model.layers.34.self_attn.q_proj": true,
433
+ "model.layers.34.self_attn.k_proj": true,
434
+ "model.layers.34.self_attn.v_proj": true,
435
+ "model.layers.34.self_attn.o_proj": true,
436
+ "model.layers.34.self_attn.q_norm": false,
437
+ "model.layers.34.self_attn.k_norm": false,
438
+ "model.layers.34.self_attn.rope": false,
439
+ "model.layers.34.mlp.gate_proj": true,
440
+ "model.layers.34.mlp.down_proj": true,
441
+ "model.layers.34.mlp.up_proj": true,
442
+ "model.layers.34.input_layernorm": false,
443
+ "model.layers.34.post_attention_layernorm": false,
444
+ "model.layers.35.self_attn.q_proj": true,
445
+ "model.layers.35.self_attn.k_proj": true,
446
+ "model.layers.35.self_attn.v_proj": true,
447
+ "model.layers.35.self_attn.o_proj": true,
448
+ "model.layers.35.self_attn.q_norm": false,
449
+ "model.layers.35.self_attn.k_norm": false,
450
+ "model.layers.35.self_attn.rope": false,
451
+ "model.layers.35.mlp.gate_proj": true,
452
+ "model.layers.35.mlp.down_proj": true,
453
+ "model.layers.35.mlp.up_proj": true,
454
+ "model.layers.35.input_layernorm": false,
455
+ "model.layers.35.post_attention_layernorm": false,
456
+ "model.layers.36.self_attn.q_proj": true,
457
+ "model.layers.36.self_attn.k_proj": true,
458
+ "model.layers.36.self_attn.v_proj": true,
459
+ "model.layers.36.self_attn.o_proj": true,
460
+ "model.layers.36.self_attn.q_norm": false,
461
+ "model.layers.36.self_attn.k_norm": false,
462
+ "model.layers.36.self_attn.rope": false,
463
+ "model.layers.36.mlp.gate_proj": true,
464
+ "model.layers.36.mlp.down_proj": true,
465
+ "model.layers.36.mlp.up_proj": true,
466
+ "model.layers.36.input_layernorm": false,
467
+ "model.layers.36.post_attention_layernorm": false,
468
+ "model.layers.37.self_attn.q_proj": true,
469
+ "model.layers.37.self_attn.k_proj": true,
470
+ "model.layers.37.self_attn.v_proj": true,
471
+ "model.layers.37.self_attn.o_proj": true,
472
+ "model.layers.37.self_attn.q_norm": false,
473
+ "model.layers.37.self_attn.k_norm": false,
474
+ "model.layers.37.self_attn.rope": false,
475
+ "model.layers.37.mlp.gate_proj": true,
476
+ "model.layers.37.mlp.down_proj": true,
477
+ "model.layers.37.mlp.up_proj": true,
478
+ "model.layers.37.input_layernorm": false,
479
+ "model.layers.37.post_attention_layernorm": false,
480
+ "model.layers.38.self_attn.q_proj": true,
481
+ "model.layers.38.self_attn.k_proj": true,
482
+ "model.layers.38.self_attn.v_proj": true,
483
+ "model.layers.38.self_attn.o_proj": true,
484
+ "model.layers.38.self_attn.q_norm": false,
485
+ "model.layers.38.self_attn.k_norm": false,
486
+ "model.layers.38.self_attn.rope": false,
487
+ "model.layers.38.mlp.gate_proj": true,
488
+ "model.layers.38.mlp.down_proj": true,
489
+ "model.layers.38.mlp.up_proj": true,
490
+ "model.layers.38.input_layernorm": false,
491
+ "model.layers.38.post_attention_layernorm": false,
492
+ "model.layers.39.self_attn.q_proj": true,
493
+ "model.layers.39.self_attn.k_proj": true,
494
+ "model.layers.39.self_attn.v_proj": true,
495
+ "model.layers.39.self_attn.o_proj": true,
496
+ "model.layers.39.self_attn.q_norm": false,
497
+ "model.layers.39.self_attn.k_norm": false,
498
+ "model.layers.39.self_attn.rope": false,
499
+ "model.layers.39.mlp.gate_proj": true,
500
+ "model.layers.39.mlp.down_proj": true,
501
+ "model.layers.39.mlp.up_proj": true,
502
+ "model.layers.39.input_layernorm": false,
503
+ "model.layers.39.post_attention_layernorm": false,
504
+ "model.layers.40.self_attn.q_proj": true,
505
+ "model.layers.40.self_attn.k_proj": true,
506
+ "model.layers.40.self_attn.v_proj": true,
507
+ "model.layers.40.self_attn.o_proj": true,
508
+ "model.layers.40.self_attn.q_norm": false,
509
+ "model.layers.40.self_attn.k_norm": false,
510
+ "model.layers.40.self_attn.rope": false,
511
+ "model.layers.40.mlp.gate_proj": true,
512
+ "model.layers.40.mlp.down_proj": true,
513
+ "model.layers.40.mlp.up_proj": true,
514
+ "model.layers.40.input_layernorm": false,
515
+ "model.layers.40.post_attention_layernorm": false,
516
+ "model.layers.41.self_attn.q_proj": true,
517
+ "model.layers.41.self_attn.k_proj": true,
518
+ "model.layers.41.self_attn.v_proj": true,
519
+ "model.layers.41.self_attn.o_proj": true,
520
+ "model.layers.41.self_attn.q_norm": false,
521
+ "model.layers.41.self_attn.k_norm": false,
522
+ "model.layers.41.self_attn.rope": false,
523
+ "model.layers.41.mlp.gate_proj": true,
524
+ "model.layers.41.mlp.down_proj": true,
525
+ "model.layers.41.mlp.up_proj": true,
526
+ "model.layers.41.input_layernorm": false,
527
+ "model.layers.41.post_attention_layernorm": false,
528
+ "model.layers.42.self_attn.q_proj": true,
529
+ "model.layers.42.self_attn.k_proj": true,
530
+ "model.layers.42.self_attn.v_proj": true,
531
+ "model.layers.42.self_attn.o_proj": true,
532
+ "model.layers.42.self_attn.q_norm": false,
533
+ "model.layers.42.self_attn.k_norm": false,
534
+ "model.layers.42.self_attn.rope": false,
535
+ "model.layers.42.mlp.gate_proj": true,
536
+ "model.layers.42.mlp.down_proj": true,
537
+ "model.layers.42.mlp.up_proj": true,
538
+ "model.layers.42.input_layernorm": false,
539
+ "model.layers.42.post_attention_layernorm": false,
540
+ "model.layers.43.self_attn.q_proj": true,
541
+ "model.layers.43.self_attn.k_proj": true,
542
+ "model.layers.43.self_attn.v_proj": true,
543
+ "model.layers.43.self_attn.o_proj": true,
544
+ "model.layers.43.self_attn.q_norm": false,
545
+ "model.layers.43.self_attn.k_norm": false,
546
+ "model.layers.43.self_attn.rope": false,
547
+ "model.layers.43.mlp.gate_proj": true,
548
+ "model.layers.43.mlp.down_proj": true,
549
+ "model.layers.43.mlp.up_proj": true,
550
+ "model.layers.43.input_layernorm": false,
551
+ "model.layers.43.post_attention_layernorm": false,
552
+ "model.layers.44.self_attn.q_proj": true,
553
+ "model.layers.44.self_attn.k_proj": true,
554
+ "model.layers.44.self_attn.v_proj": true,
555
+ "model.layers.44.self_attn.o_proj": true,
556
+ "model.layers.44.self_attn.q_norm": false,
557
+ "model.layers.44.self_attn.k_norm": false,
558
+ "model.layers.44.self_attn.rope": false,
559
+ "model.layers.44.mlp.gate_proj": true,
560
+ "model.layers.44.mlp.down_proj": true,
561
+ "model.layers.44.mlp.up_proj": true,
562
+ "model.layers.44.input_layernorm": false,
563
+ "model.layers.44.post_attention_layernorm": false,
564
+ "model.layers.45.self_attn.q_proj": true,
565
+ "model.layers.45.self_attn.k_proj": true,
566
+ "model.layers.45.self_attn.v_proj": true,
567
+ "model.layers.45.self_attn.o_proj": true,
568
+ "model.layers.45.self_attn.q_norm": false,
569
+ "model.layers.45.self_attn.k_norm": false,
570
+ "model.layers.45.self_attn.rope": false,
571
+ "model.layers.45.mlp.gate_proj": true,
572
+ "model.layers.45.mlp.down_proj": true,
573
+ "model.layers.45.mlp.up_proj": true,
574
+ "model.layers.45.input_layernorm": false,
575
+ "model.layers.45.post_attention_layernorm": false,
576
+ "model.layers.46.self_attn.q_proj": true,
577
+ "model.layers.46.self_attn.k_proj": true,
578
+ "model.layers.46.self_attn.v_proj": true,
579
+ "model.layers.46.self_attn.o_proj": true,
580
+ "model.layers.46.self_attn.q_norm": false,
581
+ "model.layers.46.self_attn.k_norm": false,
582
+ "model.layers.46.self_attn.rope": false,
583
+ "model.layers.46.mlp.gate_proj": true,
584
+ "model.layers.46.mlp.down_proj": true,
585
+ "model.layers.46.mlp.up_proj": true,
586
+ "model.layers.46.input_layernorm": false,
587
+ "model.layers.46.post_attention_layernorm": false,
588
+ "model.layers.47.self_attn.q_proj": true,
589
+ "model.layers.47.self_attn.k_proj": true,
590
+ "model.layers.47.self_attn.v_proj": true,
591
+ "model.layers.47.self_attn.o_proj": true,
592
+ "model.layers.47.self_attn.q_norm": false,
593
+ "model.layers.47.self_attn.k_norm": false,
594
+ "model.layers.47.self_attn.rope": false,
595
+ "model.layers.47.mlp.gate_proj": true,
596
+ "model.layers.47.mlp.down_proj": true,
597
+ "model.layers.47.mlp.up_proj": true,
598
+ "model.layers.47.input_layernorm": false,
599
+ "model.layers.47.post_attention_layernorm": false,
600
+ "model.layers.48.self_attn.q_proj": true,
601
+ "model.layers.48.self_attn.k_proj": true,
602
+ "model.layers.48.self_attn.v_proj": true,
603
+ "model.layers.48.self_attn.o_proj": true,
604
+ "model.layers.48.self_attn.q_norm": false,
605
+ "model.layers.48.self_attn.k_norm": false,
606
+ "model.layers.48.self_attn.rope": false,
607
+ "model.layers.48.mlp.gate_proj": true,
608
+ "model.layers.48.mlp.down_proj": true,
609
+ "model.layers.48.mlp.up_proj": true,
610
+ "model.layers.48.input_layernorm": false,
611
+ "model.layers.48.post_attention_layernorm": false,
612
+ "model.layers.49.self_attn.q_proj": true,
613
+ "model.layers.49.self_attn.k_proj": true,
614
+ "model.layers.49.self_attn.v_proj": true,
615
+ "model.layers.49.self_attn.o_proj": true,
616
+ "model.layers.49.self_attn.q_norm": false,
617
+ "model.layers.49.self_attn.k_norm": false,
618
+ "model.layers.49.self_attn.rope": false,
619
+ "model.layers.49.mlp.gate_proj": true,
620
+ "model.layers.49.mlp.down_proj": true,
621
+ "model.layers.49.mlp.up_proj": true,
622
+ "model.layers.49.input_layernorm": false,
623
+ "model.layers.49.post_attention_layernorm": false,
624
+ "model.layers.50.self_attn.q_proj": true,
625
+ "model.layers.50.self_attn.k_proj": true,
626
+ "model.layers.50.self_attn.v_proj": true,
627
+ "model.layers.50.self_attn.o_proj": true,
628
+ "model.layers.50.self_attn.q_norm": false,
629
+ "model.layers.50.self_attn.k_norm": false,
630
+ "model.layers.50.self_attn.rope": false,
631
+ "model.layers.50.mlp.gate_proj": true,
632
+ "model.layers.50.mlp.down_proj": true,
633
+ "model.layers.50.mlp.up_proj": true,
634
+ "model.layers.50.input_layernorm": false,
635
+ "model.layers.50.post_attention_layernorm": false,
636
+ "model.layers.51.self_attn.q_proj": true,
637
+ "model.layers.51.self_attn.k_proj": true,
638
+ "model.layers.51.self_attn.v_proj": true,
639
+ "model.layers.51.self_attn.o_proj": true,
640
+ "model.layers.51.self_attn.q_norm": false,
641
+ "model.layers.51.self_attn.k_norm": false,
642
+ "model.layers.51.self_attn.rope": false,
643
+ "model.layers.51.mlp.gate_proj": true,
644
+ "model.layers.51.mlp.down_proj": true,
645
+ "model.layers.51.mlp.up_proj": true,
646
+ "model.layers.51.input_layernorm": false,
647
+ "model.layers.51.post_attention_layernorm": false,
648
+ "model.layers.52.self_attn.q_proj": true,
649
+ "model.layers.52.self_attn.k_proj": true,
650
+ "model.layers.52.self_attn.v_proj": true,
651
+ "model.layers.52.self_attn.o_proj": true,
652
+ "model.layers.52.self_attn.q_norm": false,
653
+ "model.layers.52.self_attn.k_norm": false,
654
+ "model.layers.52.self_attn.rope": false,
655
+ "model.layers.52.mlp.gate_proj": true,
656
+ "model.layers.52.mlp.down_proj": true,
657
+ "model.layers.52.mlp.up_proj": true,
658
+ "model.layers.52.input_layernorm": false,
659
+ "model.layers.52.post_attention_layernorm": false,
660
+ "model.layers.53.self_attn.q_proj": true,
661
+ "model.layers.53.self_attn.k_proj": true,
662
+ "model.layers.53.self_attn.v_proj": true,
663
+ "model.layers.53.self_attn.o_proj": true,
664
+ "model.layers.53.self_attn.q_norm": false,
665
+ "model.layers.53.self_attn.k_norm": false,
666
+ "model.layers.53.self_attn.rope": false,
667
+ "model.layers.53.mlp.gate_proj": true,
668
+ "model.layers.53.mlp.down_proj": true,
669
+ "model.layers.53.mlp.up_proj": true,
670
+ "model.layers.53.input_layernorm": false,
671
+ "model.layers.53.post_attention_layernorm": false,
672
+ "model.layers.54.self_attn.q_proj": true,
673
+ "model.layers.54.self_attn.k_proj": true,
674
+ "model.layers.54.self_attn.v_proj": true,
675
+ "model.layers.54.self_attn.o_proj": true,
676
+ "model.layers.54.self_attn.q_norm": false,
677
+ "model.layers.54.self_attn.k_norm": false,
678
+ "model.layers.54.self_attn.rope": false,
679
+ "model.layers.54.mlp.gate_proj": true,
680
+ "model.layers.54.mlp.down_proj": true,
681
+ "model.layers.54.mlp.up_proj": true,
682
+ "model.layers.54.input_layernorm": false,
683
+ "model.layers.54.post_attention_layernorm": false,
684
+ "model.layers.55.self_attn.q_proj": true,
685
+ "model.layers.55.self_attn.k_proj": true,
686
+ "model.layers.55.self_attn.v_proj": true,
687
+ "model.layers.55.self_attn.o_proj": true,
688
+ "model.layers.55.self_attn.q_norm": false,
689
+ "model.layers.55.self_attn.k_norm": false,
690
+ "model.layers.55.self_attn.rope": false,
691
+ "model.layers.55.mlp.gate_proj": true,
692
+ "model.layers.55.mlp.down_proj": true,
693
+ "model.layers.55.mlp.up_proj": true,
694
+ "model.layers.55.input_layernorm": false,
695
+ "model.layers.55.post_attention_layernorm": false,
696
+ "model.layers.56.self_attn.q_proj": true,
697
+ "model.layers.56.self_attn.k_proj": true,
698
+ "model.layers.56.self_attn.v_proj": true,
699
+ "model.layers.56.self_attn.o_proj": true,
700
+ "model.layers.56.self_attn.q_norm": false,
701
+ "model.layers.56.self_attn.k_norm": false,
702
+ "model.layers.56.self_attn.rope": false,
703
+ "model.layers.56.mlp.gate_proj": true,
704
+ "model.layers.56.mlp.down_proj": true,
705
+ "model.layers.56.mlp.up_proj": true,
706
+ "model.layers.56.input_layernorm": false,
707
+ "model.layers.56.post_attention_layernorm": false,
708
+ "model.layers.57.self_attn.q_proj": true,
709
+ "model.layers.57.self_attn.k_proj": true,
710
+ "model.layers.57.self_attn.v_proj": true,
711
+ "model.layers.57.self_attn.o_proj": true,
712
+ "model.layers.57.self_attn.q_norm": false,
713
+ "model.layers.57.self_attn.k_norm": false,
714
+ "model.layers.57.self_attn.rope": false,
715
+ "model.layers.57.mlp.gate_proj": true,
716
+ "model.layers.57.mlp.down_proj": true,
717
+ "model.layers.57.mlp.up_proj": true,
718
+ "model.layers.57.input_layernorm": false,
719
+ "model.layers.57.post_attention_layernorm": false,
720
+ "model.layers.58.self_attn.q_proj": true,
721
+ "model.layers.58.self_attn.k_proj": true,
722
+ "model.layers.58.self_attn.v_proj": true,
723
+ "model.layers.58.self_attn.o_proj": true,
724
+ "model.layers.58.self_attn.q_norm": false,
725
+ "model.layers.58.self_attn.k_norm": false,
726
+ "model.layers.58.self_attn.rope": false,
727
+ "model.layers.58.mlp.gate_proj": true,
728
+ "model.layers.58.mlp.down_proj": true,
729
+ "model.layers.58.mlp.up_proj": true,
730
+ "model.layers.58.input_layernorm": false,
731
+ "model.layers.58.post_attention_layernorm": false,
732
+ "model.layers.59.self_attn.q_proj": true,
733
+ "model.layers.59.self_attn.k_proj": true,
734
+ "model.layers.59.self_attn.v_proj": true,
735
+ "model.layers.59.self_attn.o_proj": true,
736
+ "model.layers.59.self_attn.q_norm": false,
737
+ "model.layers.59.self_attn.k_norm": false,
738
+ "model.layers.59.self_attn.rope": false,
739
+ "model.layers.59.mlp.gate_proj": true,
740
+ "model.layers.59.mlp.down_proj": true,
741
+ "model.layers.59.mlp.up_proj": true,
742
+ "model.layers.59.input_layernorm": false,
743
+ "model.layers.59.post_attention_layernorm": false,
744
+ "model.layers.60.self_attn.q_proj": true,
745
+ "model.layers.60.self_attn.k_proj": true,
746
+ "model.layers.60.self_attn.v_proj": true,
747
+ "model.layers.60.self_attn.o_proj": true,
748
+ "model.layers.60.self_attn.q_norm": false,
749
+ "model.layers.60.self_attn.k_norm": false,
750
+ "model.layers.60.self_attn.rope": false,
751
+ "model.layers.60.mlp.gate_proj": true,
752
+ "model.layers.60.mlp.down_proj": true,
753
+ "model.layers.60.mlp.up_proj": true,
754
+ "model.layers.60.input_layernorm": false,
755
+ "model.layers.60.post_attention_layernorm": false,
756
+ "model.layers.61.self_attn.q_proj": true,
757
+ "model.layers.61.self_attn.k_proj": true,
758
+ "model.layers.61.self_attn.v_proj": true,
759
+ "model.layers.61.self_attn.o_proj": true,
760
+ "model.layers.61.self_attn.q_norm": false,
761
+ "model.layers.61.self_attn.k_norm": false,
762
+ "model.layers.61.self_attn.rope": false,
763
+ "model.layers.61.mlp.gate_proj": true,
764
+ "model.layers.61.mlp.down_proj": true,
765
+ "model.layers.61.mlp.up_proj": true,
766
+ "model.layers.61.input_layernorm": false,
767
+ "model.layers.61.post_attention_layernorm": false,
768
+ "model.layers.62.self_attn.q_proj": true,
769
+ "model.layers.62.self_attn.k_proj": true,
770
+ "model.layers.62.self_attn.v_proj": true,
771
+ "model.layers.62.self_attn.o_proj": true,
772
+ "model.layers.62.self_attn.q_norm": false,
773
+ "model.layers.62.self_attn.k_norm": false,
774
+ "model.layers.62.self_attn.rope": false,
775
+ "model.layers.62.mlp.gate_proj": true,
776
+ "model.layers.62.mlp.down_proj": true,
777
+ "model.layers.62.mlp.up_proj": true,
778
+ "model.layers.62.input_layernorm": false,
779
+ "model.layers.62.post_attention_layernorm": false,
780
+ "model.layers.63.self_attn.q_proj": true,
781
+ "model.layers.63.self_attn.k_proj": true,
782
+ "model.layers.63.self_attn.v_proj": true,
783
+ "model.layers.63.self_attn.o_proj": true,
784
+ "model.layers.63.self_attn.q_norm": false,
785
+ "model.layers.63.self_attn.k_norm": false,
786
+ "model.layers.63.self_attn.rope": false,
787
+ "model.layers.63.mlp.gate_proj": true,
788
+ "model.layers.63.mlp.down_proj": true,
789
+ "model.layers.63.mlp.up_proj": true,
790
+ "model.layers.63.input_layernorm": false,
791
+ "model.layers.63.post_attention_layernorm": false,
792
+ "model.norm": false,
793
+ "lm_head": true
794
+ },
795
+ "quantization_config": {
796
+ "group_size": 64,
797
+ "bits": 3,
798
+ "model.embed_tokens": true,
799
+ "model.layers.0.self_attn.q_proj": true,
800
+ "model.layers.0.self_attn.k_proj": true,
801
+ "model.layers.0.self_attn.v_proj": true,
802
+ "model.layers.0.self_attn.o_proj": true,
803
+ "model.layers.0.self_attn.q_norm": false,
804
+ "model.layers.0.self_attn.k_norm": false,
805
+ "model.layers.0.self_attn.rope": false,
806
+ "model.layers.0.mlp.gate_proj": true,
807
+ "model.layers.0.mlp.down_proj": true,
808
+ "model.layers.0.mlp.up_proj": true,
809
+ "model.layers.0.input_layernorm": false,
810
+ "model.layers.0.post_attention_layernorm": false,
811
+ "model.layers.1.self_attn.q_proj": true,
812
+ "model.layers.1.self_attn.k_proj": true,
813
+ "model.layers.1.self_attn.v_proj": true,
814
+ "model.layers.1.self_attn.o_proj": true,
815
+ "model.layers.1.self_attn.q_norm": false,
816
+ "model.layers.1.self_attn.k_norm": false,
817
+ "model.layers.1.self_attn.rope": false,
818
+ "model.layers.1.mlp.gate_proj": true,
819
+ "model.layers.1.mlp.down_proj": true,
820
+ "model.layers.1.mlp.up_proj": true,
821
+ "model.layers.1.input_layernorm": false,
822
+ "model.layers.1.post_attention_layernorm": false,
823
+ "model.layers.2.self_attn.q_proj": true,
824
+ "model.layers.2.self_attn.k_proj": true,
825
+ "model.layers.2.self_attn.v_proj": true,
826
+ "model.layers.2.self_attn.o_proj": true,
827
+ "model.layers.2.self_attn.q_norm": false,
828
+ "model.layers.2.self_attn.k_norm": false,
829
+ "model.layers.2.self_attn.rope": false,
830
+ "model.layers.2.mlp.gate_proj": true,
831
+ "model.layers.2.mlp.down_proj": true,
832
+ "model.layers.2.mlp.up_proj": true,
833
+ "model.layers.2.input_layernorm": false,
834
+ "model.layers.2.post_attention_layernorm": false,
835
+ "model.layers.3.self_attn.q_proj": true,
836
+ "model.layers.3.self_attn.k_proj": true,
837
+ "model.layers.3.self_attn.v_proj": true,
838
+ "model.layers.3.self_attn.o_proj": true,
839
+ "model.layers.3.self_attn.q_norm": false,
840
+ "model.layers.3.self_attn.k_norm": false,
841
+ "model.layers.3.self_attn.rope": false,
842
+ "model.layers.3.mlp.gate_proj": true,
843
+ "model.layers.3.mlp.down_proj": true,
844
+ "model.layers.3.mlp.up_proj": true,
845
+ "model.layers.3.input_layernorm": false,
846
+ "model.layers.3.post_attention_layernorm": false,
847
+ "model.layers.4.self_attn.q_proj": true,
848
+ "model.layers.4.self_attn.k_proj": true,
849
+ "model.layers.4.self_attn.v_proj": true,
850
+ "model.layers.4.self_attn.o_proj": true,
851
+ "model.layers.4.self_attn.q_norm": false,
852
+ "model.layers.4.self_attn.k_norm": false,
853
+ "model.layers.4.self_attn.rope": false,
854
+ "model.layers.4.mlp.gate_proj": true,
855
+ "model.layers.4.mlp.down_proj": true,
856
+ "model.layers.4.mlp.up_proj": true,
857
+ "model.layers.4.input_layernorm": false,
858
+ "model.layers.4.post_attention_layernorm": false,
859
+ "model.layers.5.self_attn.q_proj": true,
860
+ "model.layers.5.self_attn.k_proj": true,
861
+ "model.layers.5.self_attn.v_proj": true,
862
+ "model.layers.5.self_attn.o_proj": true,
863
+ "model.layers.5.self_attn.q_norm": false,
864
+ "model.layers.5.self_attn.k_norm": false,
865
+ "model.layers.5.self_attn.rope": false,
866
+ "model.layers.5.mlp.gate_proj": true,
867
+ "model.layers.5.mlp.down_proj": true,
868
+ "model.layers.5.mlp.up_proj": true,
869
+ "model.layers.5.input_layernorm": false,
870
+ "model.layers.5.post_attention_layernorm": false,
871
+ "model.layers.6.self_attn.q_proj": true,
872
+ "model.layers.6.self_attn.k_proj": true,
873
+ "model.layers.6.self_attn.v_proj": true,
874
+ "model.layers.6.self_attn.o_proj": true,
875
+ "model.layers.6.self_attn.q_norm": false,
876
+ "model.layers.6.self_attn.k_norm": false,
877
+ "model.layers.6.self_attn.rope": false,
878
+ "model.layers.6.mlp.gate_proj": true,
879
+ "model.layers.6.mlp.down_proj": true,
880
+ "model.layers.6.mlp.up_proj": true,
881
+ "model.layers.6.input_layernorm": false,
882
+ "model.layers.6.post_attention_layernorm": false,
883
+ "model.layers.7.self_attn.q_proj": true,
884
+ "model.layers.7.self_attn.k_proj": true,
885
+ "model.layers.7.self_attn.v_proj": true,
886
+ "model.layers.7.self_attn.o_proj": true,
887
+ "model.layers.7.self_attn.q_norm": false,
888
+ "model.layers.7.self_attn.k_norm": false,
889
+ "model.layers.7.self_attn.rope": false,
890
+ "model.layers.7.mlp.gate_proj": true,
891
+ "model.layers.7.mlp.down_proj": true,
892
+ "model.layers.7.mlp.up_proj": true,
893
+ "model.layers.7.input_layernorm": false,
894
+ "model.layers.7.post_attention_layernorm": false,
895
+ "model.layers.8.self_attn.q_proj": true,
896
+ "model.layers.8.self_attn.k_proj": true,
897
+ "model.layers.8.self_attn.v_proj": true,
898
+ "model.layers.8.self_attn.o_proj": true,
899
+ "model.layers.8.self_attn.q_norm": false,
900
+ "model.layers.8.self_attn.k_norm": false,
901
+ "model.layers.8.self_attn.rope": false,
902
+ "model.layers.8.mlp.gate_proj": true,
903
+ "model.layers.8.mlp.down_proj": true,
904
+ "model.layers.8.mlp.up_proj": true,
905
+ "model.layers.8.input_layernorm": false,
906
+ "model.layers.8.post_attention_layernorm": false,
907
+ "model.layers.9.self_attn.q_proj": true,
908
+ "model.layers.9.self_attn.k_proj": true,
909
+ "model.layers.9.self_attn.v_proj": true,
910
+ "model.layers.9.self_attn.o_proj": true,
911
+ "model.layers.9.self_attn.q_norm": false,
912
+ "model.layers.9.self_attn.k_norm": false,
913
+ "model.layers.9.self_attn.rope": false,
914
+ "model.layers.9.mlp.gate_proj": true,
915
+ "model.layers.9.mlp.down_proj": true,
916
+ "model.layers.9.mlp.up_proj": true,
917
+ "model.layers.9.input_layernorm": false,
918
+ "model.layers.9.post_attention_layernorm": false,
919
+ "model.layers.10.self_attn.q_proj": true,
920
+ "model.layers.10.self_attn.k_proj": true,
921
+ "model.layers.10.self_attn.v_proj": true,
922
+ "model.layers.10.self_attn.o_proj": true,
923
+ "model.layers.10.self_attn.q_norm": false,
924
+ "model.layers.10.self_attn.k_norm": false,
925
+ "model.layers.10.self_attn.rope": false,
926
+ "model.layers.10.mlp.gate_proj": true,
927
+ "model.layers.10.mlp.down_proj": true,
928
+ "model.layers.10.mlp.up_proj": true,
929
+ "model.layers.10.input_layernorm": false,
930
+ "model.layers.10.post_attention_layernorm": false,
931
+ "model.layers.11.self_attn.q_proj": true,
932
+ "model.layers.11.self_attn.k_proj": true,
933
+ "model.layers.11.self_attn.v_proj": true,
934
+ "model.layers.11.self_attn.o_proj": true,
935
+ "model.layers.11.self_attn.q_norm": false,
936
+ "model.layers.11.self_attn.k_norm": false,
937
+ "model.layers.11.self_attn.rope": false,
938
+ "model.layers.11.mlp.gate_proj": true,
939
+ "model.layers.11.mlp.down_proj": true,
940
+ "model.layers.11.mlp.up_proj": true,
941
+ "model.layers.11.input_layernorm": false,
942
+ "model.layers.11.post_attention_layernorm": false,
943
+ "model.layers.12.self_attn.q_proj": true,
944
+ "model.layers.12.self_attn.k_proj": true,
945
+ "model.layers.12.self_attn.v_proj": true,
946
+ "model.layers.12.self_attn.o_proj": true,
947
+ "model.layers.12.self_attn.q_norm": false,
948
+ "model.layers.12.self_attn.k_norm": false,
949
+ "model.layers.12.self_attn.rope": false,
950
+ "model.layers.12.mlp.gate_proj": true,
951
+ "model.layers.12.mlp.down_proj": true,
952
+ "model.layers.12.mlp.up_proj": true,
953
+ "model.layers.12.input_layernorm": false,
954
+ "model.layers.12.post_attention_layernorm": false,
955
+ "model.layers.13.self_attn.q_proj": true,
956
+ "model.layers.13.self_attn.k_proj": true,
957
+ "model.layers.13.self_attn.v_proj": true,
958
+ "model.layers.13.self_attn.o_proj": true,
959
+ "model.layers.13.self_attn.q_norm": false,
960
+ "model.layers.13.self_attn.k_norm": false,
961
+ "model.layers.13.self_attn.rope": false,
962
+ "model.layers.13.mlp.gate_proj": true,
963
+ "model.layers.13.mlp.down_proj": true,
964
+ "model.layers.13.mlp.up_proj": true,
965
+ "model.layers.13.input_layernorm": false,
966
+ "model.layers.13.post_attention_layernorm": false,
967
+ "model.layers.14.self_attn.q_proj": true,
968
+ "model.layers.14.self_attn.k_proj": true,
969
+ "model.layers.14.self_attn.v_proj": true,
970
+ "model.layers.14.self_attn.o_proj": true,
971
+ "model.layers.14.self_attn.q_norm": false,
972
+ "model.layers.14.self_attn.k_norm": false,
973
+ "model.layers.14.self_attn.rope": false,
974
+ "model.layers.14.mlp.gate_proj": true,
975
+ "model.layers.14.mlp.down_proj": true,
976
+ "model.layers.14.mlp.up_proj": true,
977
+ "model.layers.14.input_layernorm": false,
978
+ "model.layers.14.post_attention_layernorm": false,
979
+ "model.layers.15.self_attn.q_proj": true,
980
+ "model.layers.15.self_attn.k_proj": true,
981
+ "model.layers.15.self_attn.v_proj": true,
982
+ "model.layers.15.self_attn.o_proj": true,
983
+ "model.layers.15.self_attn.q_norm": false,
984
+ "model.layers.15.self_attn.k_norm": false,
985
+ "model.layers.15.self_attn.rope": false,
986
+ "model.layers.15.mlp.gate_proj": true,
987
+ "model.layers.15.mlp.down_proj": true,
988
+ "model.layers.15.mlp.up_proj": true,
989
+ "model.layers.15.input_layernorm": false,
990
+ "model.layers.15.post_attention_layernorm": false,
991
+ "model.layers.16.self_attn.q_proj": true,
992
+ "model.layers.16.self_attn.k_proj": true,
993
+ "model.layers.16.self_attn.v_proj": true,
994
+ "model.layers.16.self_attn.o_proj": true,
995
+ "model.layers.16.self_attn.q_norm": false,
996
+ "model.layers.16.self_attn.k_norm": false,
997
+ "model.layers.16.self_attn.rope": false,
998
+ "model.layers.16.mlp.gate_proj": true,
999
+ "model.layers.16.mlp.down_proj": true,
1000
+ "model.layers.16.mlp.up_proj": true,
1001
+ "model.layers.16.input_layernorm": false,
1002
+ "model.layers.16.post_attention_layernorm": false,
1003
+ "model.layers.17.self_attn.q_proj": true,
1004
+ "model.layers.17.self_attn.k_proj": true,
1005
+ "model.layers.17.self_attn.v_proj": true,
1006
+ "model.layers.17.self_attn.o_proj": true,
1007
+ "model.layers.17.self_attn.q_norm": false,
1008
+ "model.layers.17.self_attn.k_norm": false,
1009
+ "model.layers.17.self_attn.rope": false,
1010
+ "model.layers.17.mlp.gate_proj": true,
1011
+ "model.layers.17.mlp.down_proj": true,
1012
+ "model.layers.17.mlp.up_proj": true,
1013
+ "model.layers.17.input_layernorm": false,
1014
+ "model.layers.17.post_attention_layernorm": false,
1015
+ "model.layers.18.self_attn.q_proj": true,
1016
+ "model.layers.18.self_attn.k_proj": true,
1017
+ "model.layers.18.self_attn.v_proj": true,
1018
+ "model.layers.18.self_attn.o_proj": true,
1019
+ "model.layers.18.self_attn.q_norm": false,
1020
+ "model.layers.18.self_attn.k_norm": false,
1021
+ "model.layers.18.self_attn.rope": false,
1022
+ "model.layers.18.mlp.gate_proj": true,
1023
+ "model.layers.18.mlp.down_proj": true,
1024
+ "model.layers.18.mlp.up_proj": true,
1025
+ "model.layers.18.input_layernorm": false,
1026
+ "model.layers.18.post_attention_layernorm": false,
1027
+ "model.layers.19.self_attn.q_proj": true,
1028
+ "model.layers.19.self_attn.k_proj": true,
1029
+ "model.layers.19.self_attn.v_proj": true,
1030
+ "model.layers.19.self_attn.o_proj": true,
1031
+ "model.layers.19.self_attn.q_norm": false,
1032
+ "model.layers.19.self_attn.k_norm": false,
1033
+ "model.layers.19.self_attn.rope": false,
1034
+ "model.layers.19.mlp.gate_proj": true,
1035
+ "model.layers.19.mlp.down_proj": true,
1036
+ "model.layers.19.mlp.up_proj": true,
1037
+ "model.layers.19.input_layernorm": false,
1038
+ "model.layers.19.post_attention_layernorm": false,
1039
+ "model.layers.20.self_attn.q_proj": true,
1040
+ "model.layers.20.self_attn.k_proj": true,
1041
+ "model.layers.20.self_attn.v_proj": true,
1042
+ "model.layers.20.self_attn.o_proj": true,
1043
+ "model.layers.20.self_attn.q_norm": false,
1044
+ "model.layers.20.self_attn.k_norm": false,
1045
+ "model.layers.20.self_attn.rope": false,
1046
+ "model.layers.20.mlp.gate_proj": true,
1047
+ "model.layers.20.mlp.down_proj": true,
1048
+ "model.layers.20.mlp.up_proj": true,
1049
+ "model.layers.20.input_layernorm": false,
1050
+ "model.layers.20.post_attention_layernorm": false,
1051
+ "model.layers.21.self_attn.q_proj": true,
1052
+ "model.layers.21.self_attn.k_proj": true,
1053
+ "model.layers.21.self_attn.v_proj": true,
1054
+ "model.layers.21.self_attn.o_proj": true,
1055
+ "model.layers.21.self_attn.q_norm": false,
1056
+ "model.layers.21.self_attn.k_norm": false,
1057
+ "model.layers.21.self_attn.rope": false,
1058
+ "model.layers.21.mlp.gate_proj": true,
1059
+ "model.layers.21.mlp.down_proj": true,
1060
+ "model.layers.21.mlp.up_proj": true,
1061
+ "model.layers.21.input_layernorm": false,
1062
+ "model.layers.21.post_attention_layernorm": false,
1063
+ "model.layers.22.self_attn.q_proj": true,
1064
+ "model.layers.22.self_attn.k_proj": true,
1065
+ "model.layers.22.self_attn.v_proj": true,
1066
+ "model.layers.22.self_attn.o_proj": true,
1067
+ "model.layers.22.self_attn.q_norm": false,
1068
+ "model.layers.22.self_attn.k_norm": false,
1069
+ "model.layers.22.self_attn.rope": false,
1070
+ "model.layers.22.mlp.gate_proj": true,
1071
+ "model.layers.22.mlp.down_proj": true,
1072
+ "model.layers.22.mlp.up_proj": true,
1073
+ "model.layers.22.input_layernorm": false,
1074
+ "model.layers.22.post_attention_layernorm": false,
1075
+ "model.layers.23.self_attn.q_proj": true,
1076
+ "model.layers.23.self_attn.k_proj": true,
1077
+ "model.layers.23.self_attn.v_proj": true,
1078
+ "model.layers.23.self_attn.o_proj": true,
1079
+ "model.layers.23.self_attn.q_norm": false,
1080
+ "model.layers.23.self_attn.k_norm": false,
1081
+ "model.layers.23.self_attn.rope": false,
1082
+ "model.layers.23.mlp.gate_proj": true,
1083
+ "model.layers.23.mlp.down_proj": true,
1084
+ "model.layers.23.mlp.up_proj": true,
1085
+ "model.layers.23.input_layernorm": false,
1086
+ "model.layers.23.post_attention_layernorm": false,
1087
+ "model.layers.24.self_attn.q_proj": true,
1088
+ "model.layers.24.self_attn.k_proj": true,
1089
+ "model.layers.24.self_attn.v_proj": true,
1090
+ "model.layers.24.self_attn.o_proj": true,
1091
+ "model.layers.24.self_attn.q_norm": false,
1092
+ "model.layers.24.self_attn.k_norm": false,
1093
+ "model.layers.24.self_attn.rope": false,
1094
+ "model.layers.24.mlp.gate_proj": true,
1095
+ "model.layers.24.mlp.down_proj": true,
1096
+ "model.layers.24.mlp.up_proj": true,
1097
+ "model.layers.24.input_layernorm": false,
1098
+ "model.layers.24.post_attention_layernorm": false,
1099
+ "model.layers.25.self_attn.q_proj": true,
1100
+ "model.layers.25.self_attn.k_proj": true,
1101
+ "model.layers.25.self_attn.v_proj": true,
1102
+ "model.layers.25.self_attn.o_proj": true,
1103
+ "model.layers.25.self_attn.q_norm": false,
1104
+ "model.layers.25.self_attn.k_norm": false,
1105
+ "model.layers.25.self_attn.rope": false,
1106
+ "model.layers.25.mlp.gate_proj": true,
1107
+ "model.layers.25.mlp.down_proj": true,
1108
+ "model.layers.25.mlp.up_proj": true,
1109
+ "model.layers.25.input_layernorm": false,
1110
+ "model.layers.25.post_attention_layernorm": false,
1111
+ "model.layers.26.self_attn.q_proj": true,
1112
+ "model.layers.26.self_attn.k_proj": true,
1113
+ "model.layers.26.self_attn.v_proj": true,
1114
+ "model.layers.26.self_attn.o_proj": true,
1115
+ "model.layers.26.self_attn.q_norm": false,
1116
+ "model.layers.26.self_attn.k_norm": false,
1117
+ "model.layers.26.self_attn.rope": false,
1118
+ "model.layers.26.mlp.gate_proj": true,
1119
+ "model.layers.26.mlp.down_proj": true,
1120
+ "model.layers.26.mlp.up_proj": true,
1121
+ "model.layers.26.input_layernorm": false,
1122
+ "model.layers.26.post_attention_layernorm": false,
1123
+ "model.layers.27.self_attn.q_proj": true,
1124
+ "model.layers.27.self_attn.k_proj": true,
1125
+ "model.layers.27.self_attn.v_proj": true,
1126
+ "model.layers.27.self_attn.o_proj": true,
1127
+ "model.layers.27.self_attn.q_norm": false,
1128
+ "model.layers.27.self_attn.k_norm": false,
1129
+ "model.layers.27.self_attn.rope": false,
1130
+ "model.layers.27.mlp.gate_proj": true,
1131
+ "model.layers.27.mlp.down_proj": true,
1132
+ "model.layers.27.mlp.up_proj": true,
1133
+ "model.layers.27.input_layernorm": false,
1134
+ "model.layers.27.post_attention_layernorm": false,
1135
+ "model.layers.28.self_attn.q_proj": true,
1136
+ "model.layers.28.self_attn.k_proj": true,
1137
+ "model.layers.28.self_attn.v_proj": true,
1138
+ "model.layers.28.self_attn.o_proj": true,
1139
+ "model.layers.28.self_attn.q_norm": false,
1140
+ "model.layers.28.self_attn.k_norm": false,
1141
+ "model.layers.28.self_attn.rope": false,
1142
+ "model.layers.28.mlp.gate_proj": true,
1143
+ "model.layers.28.mlp.down_proj": true,
1144
+ "model.layers.28.mlp.up_proj": true,
1145
+ "model.layers.28.input_layernorm": false,
1146
+ "model.layers.28.post_attention_layernorm": false,
1147
+ "model.layers.29.self_attn.q_proj": true,
1148
+ "model.layers.29.self_attn.k_proj": true,
1149
+ "model.layers.29.self_attn.v_proj": true,
1150
+ "model.layers.29.self_attn.o_proj": true,
1151
+ "model.layers.29.self_attn.q_norm": false,
1152
+ "model.layers.29.self_attn.k_norm": false,
1153
+ "model.layers.29.self_attn.rope": false,
1154
+ "model.layers.29.mlp.gate_proj": true,
1155
+ "model.layers.29.mlp.down_proj": true,
1156
+ "model.layers.29.mlp.up_proj": true,
1157
+ "model.layers.29.input_layernorm": false,
1158
+ "model.layers.29.post_attention_layernorm": false,
1159
+ "model.layers.30.self_attn.q_proj": true,
1160
+ "model.layers.30.self_attn.k_proj": true,
1161
+ "model.layers.30.self_attn.v_proj": true,
1162
+ "model.layers.30.self_attn.o_proj": true,
1163
+ "model.layers.30.self_attn.q_norm": false,
1164
+ "model.layers.30.self_attn.k_norm": false,
1165
+ "model.layers.30.self_attn.rope": false,
1166
+ "model.layers.30.mlp.gate_proj": true,
1167
+ "model.layers.30.mlp.down_proj": true,
1168
+ "model.layers.30.mlp.up_proj": true,
1169
+ "model.layers.30.input_layernorm": false,
1170
+ "model.layers.30.post_attention_layernorm": false,
1171
+ "model.layers.31.self_attn.q_proj": true,
1172
+ "model.layers.31.self_attn.k_proj": true,
1173
+ "model.layers.31.self_attn.v_proj": true,
1174
+ "model.layers.31.self_attn.o_proj": true,
1175
+ "model.layers.31.self_attn.q_norm": false,
1176
+ "model.layers.31.self_attn.k_norm": false,
1177
+ "model.layers.31.self_attn.rope": false,
1178
+ "model.layers.31.mlp.gate_proj": true,
1179
+ "model.layers.31.mlp.down_proj": true,
1180
+ "model.layers.31.mlp.up_proj": true,
1181
+ "model.layers.31.input_layernorm": false,
1182
+ "model.layers.31.post_attention_layernorm": false,
1183
+ "model.layers.32.self_attn.q_proj": true,
1184
+ "model.layers.32.self_attn.k_proj": true,
1185
+ "model.layers.32.self_attn.v_proj": true,
1186
+ "model.layers.32.self_attn.o_proj": true,
1187
+ "model.layers.32.self_attn.q_norm": false,
1188
+ "model.layers.32.self_attn.k_norm": false,
1189
+ "model.layers.32.self_attn.rope": false,
1190
+ "model.layers.32.mlp.gate_proj": true,
1191
+ "model.layers.32.mlp.down_proj": true,
1192
+ "model.layers.32.mlp.up_proj": true,
1193
+ "model.layers.32.input_layernorm": false,
1194
+ "model.layers.32.post_attention_layernorm": false,
1195
+ "model.layers.33.self_attn.q_proj": true,
1196
+ "model.layers.33.self_attn.k_proj": true,
1197
+ "model.layers.33.self_attn.v_proj": true,
1198
+ "model.layers.33.self_attn.o_proj": true,
1199
+ "model.layers.33.self_attn.q_norm": false,
1200
+ "model.layers.33.self_attn.k_norm": false,
1201
+ "model.layers.33.self_attn.rope": false,
1202
+ "model.layers.33.mlp.gate_proj": true,
1203
+ "model.layers.33.mlp.down_proj": true,
1204
+ "model.layers.33.mlp.up_proj": true,
1205
+ "model.layers.33.input_layernorm": false,
1206
+ "model.layers.33.post_attention_layernorm": false,
1207
+ "model.layers.34.self_attn.q_proj": true,
1208
+ "model.layers.34.self_attn.k_proj": true,
1209
+ "model.layers.34.self_attn.v_proj": true,
1210
+ "model.layers.34.self_attn.o_proj": true,
1211
+ "model.layers.34.self_attn.q_norm": false,
1212
+ "model.layers.34.self_attn.k_norm": false,
1213
+ "model.layers.34.self_attn.rope": false,
1214
+ "model.layers.34.mlp.gate_proj": true,
1215
+ "model.layers.34.mlp.down_proj": true,
1216
+ "model.layers.34.mlp.up_proj": true,
1217
+ "model.layers.34.input_layernorm": false,
1218
+ "model.layers.34.post_attention_layernorm": false,
1219
+ "model.layers.35.self_attn.q_proj": true,
1220
+ "model.layers.35.self_attn.k_proj": true,
1221
+ "model.layers.35.self_attn.v_proj": true,
1222
+ "model.layers.35.self_attn.o_proj": true,
1223
+ "model.layers.35.self_attn.q_norm": false,
1224
+ "model.layers.35.self_attn.k_norm": false,
1225
+ "model.layers.35.self_attn.rope": false,
1226
+ "model.layers.35.mlp.gate_proj": true,
1227
+ "model.layers.35.mlp.down_proj": true,
1228
+ "model.layers.35.mlp.up_proj": true,
1229
+ "model.layers.35.input_layernorm": false,
1230
+ "model.layers.35.post_attention_layernorm": false,
1231
+ "model.layers.36.self_attn.q_proj": true,
1232
+ "model.layers.36.self_attn.k_proj": true,
1233
+ "model.layers.36.self_attn.v_proj": true,
1234
+ "model.layers.36.self_attn.o_proj": true,
1235
+ "model.layers.36.self_attn.q_norm": false,
1236
+ "model.layers.36.self_attn.k_norm": false,
1237
+ "model.layers.36.self_attn.rope": false,
1238
+ "model.layers.36.mlp.gate_proj": true,
1239
+ "model.layers.36.mlp.down_proj": true,
1240
+ "model.layers.36.mlp.up_proj": true,
1241
+ "model.layers.36.input_layernorm": false,
1242
+ "model.layers.36.post_attention_layernorm": false,
1243
+ "model.layers.37.self_attn.q_proj": true,
1244
+ "model.layers.37.self_attn.k_proj": true,
1245
+ "model.layers.37.self_attn.v_proj": true,
1246
+ "model.layers.37.self_attn.o_proj": true,
1247
+ "model.layers.37.self_attn.q_norm": false,
1248
+ "model.layers.37.self_attn.k_norm": false,
1249
+ "model.layers.37.self_attn.rope": false,
1250
+ "model.layers.37.mlp.gate_proj": true,
1251
+ "model.layers.37.mlp.down_proj": true,
1252
+ "model.layers.37.mlp.up_proj": true,
1253
+ "model.layers.37.input_layernorm": false,
1254
+ "model.layers.37.post_attention_layernorm": false,
1255
+ "model.layers.38.self_attn.q_proj": true,
1256
+ "model.layers.38.self_attn.k_proj": true,
1257
+ "model.layers.38.self_attn.v_proj": true,
1258
+ "model.layers.38.self_attn.o_proj": true,
1259
+ "model.layers.38.self_attn.q_norm": false,
1260
+ "model.layers.38.self_attn.k_norm": false,
1261
+ "model.layers.38.self_attn.rope": false,
1262
+ "model.layers.38.mlp.gate_proj": true,
1263
+ "model.layers.38.mlp.down_proj": true,
1264
+ "model.layers.38.mlp.up_proj": true,
1265
+ "model.layers.38.input_layernorm": false,
1266
+ "model.layers.38.post_attention_layernorm": false,
1267
+ "model.layers.39.self_attn.q_proj": true,
1268
+ "model.layers.39.self_attn.k_proj": true,
1269
+ "model.layers.39.self_attn.v_proj": true,
1270
+ "model.layers.39.self_attn.o_proj": true,
1271
+ "model.layers.39.self_attn.q_norm": false,
1272
+ "model.layers.39.self_attn.k_norm": false,
1273
+ "model.layers.39.self_attn.rope": false,
1274
+ "model.layers.39.mlp.gate_proj": true,
1275
+ "model.layers.39.mlp.down_proj": true,
1276
+ "model.layers.39.mlp.up_proj": true,
1277
+ "model.layers.39.input_layernorm": false,
1278
+ "model.layers.39.post_attention_layernorm": false,
1279
+ "model.layers.40.self_attn.q_proj": true,
1280
+ "model.layers.40.self_attn.k_proj": true,
1281
+ "model.layers.40.self_attn.v_proj": true,
1282
+ "model.layers.40.self_attn.o_proj": true,
1283
+ "model.layers.40.self_attn.q_norm": false,
1284
+ "model.layers.40.self_attn.k_norm": false,
1285
+ "model.layers.40.self_attn.rope": false,
1286
+ "model.layers.40.mlp.gate_proj": true,
1287
+ "model.layers.40.mlp.down_proj": true,
1288
+ "model.layers.40.mlp.up_proj": true,
1289
+ "model.layers.40.input_layernorm": false,
1290
+ "model.layers.40.post_attention_layernorm": false,
1291
+ "model.layers.41.self_attn.q_proj": true,
1292
+ "model.layers.41.self_attn.k_proj": true,
1293
+ "model.layers.41.self_attn.v_proj": true,
1294
+ "model.layers.41.self_attn.o_proj": true,
1295
+ "model.layers.41.self_attn.q_norm": false,
1296
+ "model.layers.41.self_attn.k_norm": false,
1297
+ "model.layers.41.self_attn.rope": false,
1298
+ "model.layers.41.mlp.gate_proj": true,
1299
+ "model.layers.41.mlp.down_proj": true,
1300
+ "model.layers.41.mlp.up_proj": true,
1301
+ "model.layers.41.input_layernorm": false,
1302
+ "model.layers.41.post_attention_layernorm": false,
1303
+ "model.layers.42.self_attn.q_proj": true,
1304
+ "model.layers.42.self_attn.k_proj": true,
1305
+ "model.layers.42.self_attn.v_proj": true,
1306
+ "model.layers.42.self_attn.o_proj": true,
1307
+ "model.layers.42.self_attn.q_norm": false,
1308
+ "model.layers.42.self_attn.k_norm": false,
1309
+ "model.layers.42.self_attn.rope": false,
1310
+ "model.layers.42.mlp.gate_proj": true,
1311
+ "model.layers.42.mlp.down_proj": true,
1312
+ "model.layers.42.mlp.up_proj": true,
1313
+ "model.layers.42.input_layernorm": false,
1314
+ "model.layers.42.post_attention_layernorm": false,
1315
+ "model.layers.43.self_attn.q_proj": true,
1316
+ "model.layers.43.self_attn.k_proj": true,
1317
+ "model.layers.43.self_attn.v_proj": true,
1318
+ "model.layers.43.self_attn.o_proj": true,
1319
+ "model.layers.43.self_attn.q_norm": false,
1320
+ "model.layers.43.self_attn.k_norm": false,
1321
+ "model.layers.43.self_attn.rope": false,
1322
+ "model.layers.43.mlp.gate_proj": true,
1323
+ "model.layers.43.mlp.down_proj": true,
1324
+ "model.layers.43.mlp.up_proj": true,
1325
+ "model.layers.43.input_layernorm": false,
1326
+ "model.layers.43.post_attention_layernorm": false,
1327
+ "model.layers.44.self_attn.q_proj": true,
1328
+ "model.layers.44.self_attn.k_proj": true,
1329
+ "model.layers.44.self_attn.v_proj": true,
1330
+ "model.layers.44.self_attn.o_proj": true,
1331
+ "model.layers.44.self_attn.q_norm": false,
1332
+ "model.layers.44.self_attn.k_norm": false,
1333
+ "model.layers.44.self_attn.rope": false,
1334
+ "model.layers.44.mlp.gate_proj": true,
1335
+ "model.layers.44.mlp.down_proj": true,
1336
+ "model.layers.44.mlp.up_proj": true,
1337
+ "model.layers.44.input_layernorm": false,
1338
+ "model.layers.44.post_attention_layernorm": false,
1339
+ "model.layers.45.self_attn.q_proj": true,
1340
+ "model.layers.45.self_attn.k_proj": true,
1341
+ "model.layers.45.self_attn.v_proj": true,
1342
+ "model.layers.45.self_attn.o_proj": true,
1343
+ "model.layers.45.self_attn.q_norm": false,
1344
+ "model.layers.45.self_attn.k_norm": false,
1345
+ "model.layers.45.self_attn.rope": false,
1346
+ "model.layers.45.mlp.gate_proj": true,
1347
+ "model.layers.45.mlp.down_proj": true,
1348
+ "model.layers.45.mlp.up_proj": true,
1349
+ "model.layers.45.input_layernorm": false,
1350
+ "model.layers.45.post_attention_layernorm": false,
1351
+ "model.layers.46.self_attn.q_proj": true,
1352
+ "model.layers.46.self_attn.k_proj": true,
1353
+ "model.layers.46.self_attn.v_proj": true,
1354
+ "model.layers.46.self_attn.o_proj": true,
1355
+ "model.layers.46.self_attn.q_norm": false,
1356
+ "model.layers.46.self_attn.k_norm": false,
1357
+ "model.layers.46.self_attn.rope": false,
1358
+ "model.layers.46.mlp.gate_proj": true,
1359
+ "model.layers.46.mlp.down_proj": true,
1360
+ "model.layers.46.mlp.up_proj": true,
1361
+ "model.layers.46.input_layernorm": false,
1362
+ "model.layers.46.post_attention_layernorm": false,
1363
+ "model.layers.47.self_attn.q_proj": true,
1364
+ "model.layers.47.self_attn.k_proj": true,
1365
+ "model.layers.47.self_attn.v_proj": true,
1366
+ "model.layers.47.self_attn.o_proj": true,
1367
+ "model.layers.47.self_attn.q_norm": false,
1368
+ "model.layers.47.self_attn.k_norm": false,
1369
+ "model.layers.47.self_attn.rope": false,
1370
+ "model.layers.47.mlp.gate_proj": true,
1371
+ "model.layers.47.mlp.down_proj": true,
1372
+ "model.layers.47.mlp.up_proj": true,
1373
+ "model.layers.47.input_layernorm": false,
1374
+ "model.layers.47.post_attention_layernorm": false,
1375
+ "model.layers.48.self_attn.q_proj": true,
1376
+ "model.layers.48.self_attn.k_proj": true,
1377
+ "model.layers.48.self_attn.v_proj": true,
1378
+ "model.layers.48.self_attn.o_proj": true,
1379
+ "model.layers.48.self_attn.q_norm": false,
1380
+ "model.layers.48.self_attn.k_norm": false,
1381
+ "model.layers.48.self_attn.rope": false,
1382
+ "model.layers.48.mlp.gate_proj": true,
1383
+ "model.layers.48.mlp.down_proj": true,
1384
+ "model.layers.48.mlp.up_proj": true,
1385
+ "model.layers.48.input_layernorm": false,
1386
+ "model.layers.48.post_attention_layernorm": false,
1387
+ "model.layers.49.self_attn.q_proj": true,
1388
+ "model.layers.49.self_attn.k_proj": true,
1389
+ "model.layers.49.self_attn.v_proj": true,
1390
+ "model.layers.49.self_attn.o_proj": true,
1391
+ "model.layers.49.self_attn.q_norm": false,
1392
+ "model.layers.49.self_attn.k_norm": false,
1393
+ "model.layers.49.self_attn.rope": false,
1394
+ "model.layers.49.mlp.gate_proj": true,
1395
+ "model.layers.49.mlp.down_proj": true,
1396
+ "model.layers.49.mlp.up_proj": true,
1397
+ "model.layers.49.input_layernorm": false,
1398
+ "model.layers.49.post_attention_layernorm": false,
1399
+ "model.layers.50.self_attn.q_proj": true,
1400
+ "model.layers.50.self_attn.k_proj": true,
1401
+ "model.layers.50.self_attn.v_proj": true,
1402
+ "model.layers.50.self_attn.o_proj": true,
1403
+ "model.layers.50.self_attn.q_norm": false,
1404
+ "model.layers.50.self_attn.k_norm": false,
1405
+ "model.layers.50.self_attn.rope": false,
1406
+ "model.layers.50.mlp.gate_proj": true,
1407
+ "model.layers.50.mlp.down_proj": true,
1408
+ "model.layers.50.mlp.up_proj": true,
1409
+ "model.layers.50.input_layernorm": false,
1410
+ "model.layers.50.post_attention_layernorm": false,
1411
+ "model.layers.51.self_attn.q_proj": true,
1412
+ "model.layers.51.self_attn.k_proj": true,
1413
+ "model.layers.51.self_attn.v_proj": true,
1414
+ "model.layers.51.self_attn.o_proj": true,
1415
+ "model.layers.51.self_attn.q_norm": false,
1416
+ "model.layers.51.self_attn.k_norm": false,
1417
+ "model.layers.51.self_attn.rope": false,
1418
+ "model.layers.51.mlp.gate_proj": true,
1419
+ "model.layers.51.mlp.down_proj": true,
1420
+ "model.layers.51.mlp.up_proj": true,
1421
+ "model.layers.51.input_layernorm": false,
1422
+ "model.layers.51.post_attention_layernorm": false,
1423
+ "model.layers.52.self_attn.q_proj": true,
1424
+ "model.layers.52.self_attn.k_proj": true,
1425
+ "model.layers.52.self_attn.v_proj": true,
1426
+ "model.layers.52.self_attn.o_proj": true,
1427
+ "model.layers.52.self_attn.q_norm": false,
1428
+ "model.layers.52.self_attn.k_norm": false,
1429
+ "model.layers.52.self_attn.rope": false,
1430
+ "model.layers.52.mlp.gate_proj": true,
1431
+ "model.layers.52.mlp.down_proj": true,
1432
+ "model.layers.52.mlp.up_proj": true,
1433
+ "model.layers.52.input_layernorm": false,
1434
+ "model.layers.52.post_attention_layernorm": false,
1435
+ "model.layers.53.self_attn.q_proj": true,
1436
+ "model.layers.53.self_attn.k_proj": true,
1437
+ "model.layers.53.self_attn.v_proj": true,
1438
+ "model.layers.53.self_attn.o_proj": true,
1439
+ "model.layers.53.self_attn.q_norm": false,
1440
+ "model.layers.53.self_attn.k_norm": false,
1441
+ "model.layers.53.self_attn.rope": false,
1442
+ "model.layers.53.mlp.gate_proj": true,
1443
+ "model.layers.53.mlp.down_proj": true,
1444
+ "model.layers.53.mlp.up_proj": true,
1445
+ "model.layers.53.input_layernorm": false,
1446
+ "model.layers.53.post_attention_layernorm": false,
1447
+ "model.layers.54.self_attn.q_proj": true,
1448
+ "model.layers.54.self_attn.k_proj": true,
1449
+ "model.layers.54.self_attn.v_proj": true,
1450
+ "model.layers.54.self_attn.o_proj": true,
1451
+ "model.layers.54.self_attn.q_norm": false,
1452
+ "model.layers.54.self_attn.k_norm": false,
1453
+ "model.layers.54.self_attn.rope": false,
1454
+ "model.layers.54.mlp.gate_proj": true,
1455
+ "model.layers.54.mlp.down_proj": true,
1456
+ "model.layers.54.mlp.up_proj": true,
1457
+ "model.layers.54.input_layernorm": false,
1458
+ "model.layers.54.post_attention_layernorm": false,
1459
+ "model.layers.55.self_attn.q_proj": true,
1460
+ "model.layers.55.self_attn.k_proj": true,
1461
+ "model.layers.55.self_attn.v_proj": true,
1462
+ "model.layers.55.self_attn.o_proj": true,
1463
+ "model.layers.55.self_attn.q_norm": false,
1464
+ "model.layers.55.self_attn.k_norm": false,
1465
+ "model.layers.55.self_attn.rope": false,
1466
+ "model.layers.55.mlp.gate_proj": true,
1467
+ "model.layers.55.mlp.down_proj": true,
1468
+ "model.layers.55.mlp.up_proj": true,
1469
+ "model.layers.55.input_layernorm": false,
1470
+ "model.layers.55.post_attention_layernorm": false,
1471
+ "model.layers.56.self_attn.q_proj": true,
1472
+ "model.layers.56.self_attn.k_proj": true,
1473
+ "model.layers.56.self_attn.v_proj": true,
1474
+ "model.layers.56.self_attn.o_proj": true,
1475
+ "model.layers.56.self_attn.q_norm": false,
1476
+ "model.layers.56.self_attn.k_norm": false,
1477
+ "model.layers.56.self_attn.rope": false,
1478
+ "model.layers.56.mlp.gate_proj": true,
1479
+ "model.layers.56.mlp.down_proj": true,
1480
+ "model.layers.56.mlp.up_proj": true,
1481
+ "model.layers.56.input_layernorm": false,
1482
+ "model.layers.56.post_attention_layernorm": false,
1483
+ "model.layers.57.self_attn.q_proj": true,
1484
+ "model.layers.57.self_attn.k_proj": true,
1485
+ "model.layers.57.self_attn.v_proj": true,
1486
+ "model.layers.57.self_attn.o_proj": true,
1487
+ "model.layers.57.self_attn.q_norm": false,
1488
+ "model.layers.57.self_attn.k_norm": false,
1489
+ "model.layers.57.self_attn.rope": false,
1490
+ "model.layers.57.mlp.gate_proj": true,
1491
+ "model.layers.57.mlp.down_proj": true,
1492
+ "model.layers.57.mlp.up_proj": true,
1493
+ "model.layers.57.input_layernorm": false,
1494
+ "model.layers.57.post_attention_layernorm": false,
1495
+ "model.layers.58.self_attn.q_proj": true,
1496
+ "model.layers.58.self_attn.k_proj": true,
1497
+ "model.layers.58.self_attn.v_proj": true,
1498
+ "model.layers.58.self_attn.o_proj": true,
1499
+ "model.layers.58.self_attn.q_norm": false,
1500
+ "model.layers.58.self_attn.k_norm": false,
1501
+ "model.layers.58.self_attn.rope": false,
1502
+ "model.layers.58.mlp.gate_proj": true,
1503
+ "model.layers.58.mlp.down_proj": true,
1504
+ "model.layers.58.mlp.up_proj": true,
1505
+ "model.layers.58.input_layernorm": false,
1506
+ "model.layers.58.post_attention_layernorm": false,
1507
+ "model.layers.59.self_attn.q_proj": true,
1508
+ "model.layers.59.self_attn.k_proj": true,
1509
+ "model.layers.59.self_attn.v_proj": true,
1510
+ "model.layers.59.self_attn.o_proj": true,
1511
+ "model.layers.59.self_attn.q_norm": false,
1512
+ "model.layers.59.self_attn.k_norm": false,
1513
+ "model.layers.59.self_attn.rope": false,
1514
+ "model.layers.59.mlp.gate_proj": true,
1515
+ "model.layers.59.mlp.down_proj": true,
1516
+ "model.layers.59.mlp.up_proj": true,
1517
+ "model.layers.59.input_layernorm": false,
1518
+ "model.layers.59.post_attention_layernorm": false,
1519
+ "model.layers.60.self_attn.q_proj": true,
1520
+ "model.layers.60.self_attn.k_proj": true,
1521
+ "model.layers.60.self_attn.v_proj": true,
1522
+ "model.layers.60.self_attn.o_proj": true,
1523
+ "model.layers.60.self_attn.q_norm": false,
1524
+ "model.layers.60.self_attn.k_norm": false,
1525
+ "model.layers.60.self_attn.rope": false,
1526
+ "model.layers.60.mlp.gate_proj": true,
1527
+ "model.layers.60.mlp.down_proj": true,
1528
+ "model.layers.60.mlp.up_proj": true,
1529
+ "model.layers.60.input_layernorm": false,
1530
+ "model.layers.60.post_attention_layernorm": false,
1531
+ "model.layers.61.self_attn.q_proj": true,
1532
+ "model.layers.61.self_attn.k_proj": true,
1533
+ "model.layers.61.self_attn.v_proj": true,
1534
+ "model.layers.61.self_attn.o_proj": true,
1535
+ "model.layers.61.self_attn.q_norm": false,
1536
+ "model.layers.61.self_attn.k_norm": false,
1537
+ "model.layers.61.self_attn.rope": false,
1538
+ "model.layers.61.mlp.gate_proj": true,
1539
+ "model.layers.61.mlp.down_proj": true,
1540
+ "model.layers.61.mlp.up_proj": true,
1541
+ "model.layers.61.input_layernorm": false,
1542
+ "model.layers.61.post_attention_layernorm": false,
1543
+ "model.layers.62.self_attn.q_proj": true,
1544
+ "model.layers.62.self_attn.k_proj": true,
1545
+ "model.layers.62.self_attn.v_proj": true,
1546
+ "model.layers.62.self_attn.o_proj": true,
1547
+ "model.layers.62.self_attn.q_norm": false,
1548
+ "model.layers.62.self_attn.k_norm": false,
1549
+ "model.layers.62.self_attn.rope": false,
1550
+ "model.layers.62.mlp.gate_proj": true,
1551
+ "model.layers.62.mlp.down_proj": true,
1552
+ "model.layers.62.mlp.up_proj": true,
1553
+ "model.layers.62.input_layernorm": false,
1554
+ "model.layers.62.post_attention_layernorm": false,
1555
+ "model.layers.63.self_attn.q_proj": true,
1556
+ "model.layers.63.self_attn.k_proj": true,
1557
+ "model.layers.63.self_attn.v_proj": true,
1558
+ "model.layers.63.self_attn.o_proj": true,
1559
+ "model.layers.63.self_attn.q_norm": false,
1560
+ "model.layers.63.self_attn.k_norm": false,
1561
+ "model.layers.63.self_attn.rope": false,
1562
+ "model.layers.63.mlp.gate_proj": true,
1563
+ "model.layers.63.mlp.down_proj": true,
1564
+ "model.layers.63.mlp.up_proj": true,
1565
+ "model.layers.63.input_layernorm": false,
1566
+ "model.layers.63.post_attention_layernorm": false,
1567
+ "model.norm": false,
1568
+ "lm_head": true
1569
+ },
1570
+ "rms_norm_eps": 1e-06,
1571
+ "rope_scaling": null,
1572
+ "rope_theta": 1000000,
1573
+ "sliding_window": null,
1574
+ "tie_word_embeddings": false,
1575
+ "torch_dtype": "bfloat16",
1576
+ "transformers_version": "4.51.0",
1577
+ "use_cache": true,
1578
+ "use_sliding_window": false,
1579
+ "vocab_size": 151936
1580
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc8b4ca200e8579b810e0edbe2aebd7a0ec824fc089ec540ed15a7fc84c57fc
3
+ size 5345872109
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b827a3779383f5de84f9b473505ea58b76e5493ffda6c171d0d88f1aeeaeaacb
3
+ size 5333588325
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012029667fc60683f99c9828442ef4209c7684a6dc51fac044e4424b9d146d8b
3
+ size 3655209582
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "<|endoftext|>",
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 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff