Hugging Face's logo

CallMcMargin
/
Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6

Text Generation
MLX
Safetensors
mistral
conversational
4-bit precision
Model card Files
xet
Community
CallMcMargin commited on
Commit
fa334cb
·
verified ·
1 Parent(s): 6c1c4e7

Add files using upload-large-folder tool

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. README.md +46 -0
  3. chat_template.jinja +87 -0
  4. config.json +2292 -0
  5. generation_config.json +6 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +935 -0
  9. special_tokens_map.json +23 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - fr
6
+ - de
7
+ - es
8
+ - it
9
+ - pt
10
+ - ru
11
+ - zh
12
+ - ja
13
+ base_model: grimjim/Nemo-Instruct-2407-MPOA-v4-12B
14
+ pipeline_tag: text-generation
15
+ library_name: mlx
16
+ tags:
17
+ - mlx
18
+ ---
19
+
20
+ # CallMcMargin/Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6
21
+
22
+ This model [CallMcMargin/Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6](https://huggingface.co/CallMcMargin/Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6) was
23
+ converted to MLX format from [grimjim/Nemo-Instruct-2407-MPOA-v4-12B](https://huggingface.co/grimjim/Nemo-Instruct-2407-MPOA-v4-12B)
24
+ using mlx-lm version **0.28.4**.
25
+
26
+ ## Use with mlx
27
+
28
+ ```bash
29
+ pip install mlx-lm
30
+ ```
31
+
32
+ ```python
33
+ from mlx_lm import load, generate
34
+
35
+ model, tokenizer = load("CallMcMargin/Nemo-Instruct-2407-MPOA-v4-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6")
36
+
37
+ prompt = "hello"
38
+
39
+ if tokenizer.chat_template is not None:
40
+ messages = [{"role": "user", "content": prompt}]
41
+ prompt = tokenizer.apply_chat_template(
42
+ messages, add_generation_prompt=True
43
+ )
44
+
45
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
46
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if messages[0]["role"] == "system" %}
2
+ {%- set system_message = messages[0]["content"] %}
3
+ {%- set loop_messages = messages[1:] %}
4
+ {%- else %}
5
+ {%- set loop_messages = messages %}
6
+ {%- endif %}
7
+ {%- if not tools is defined %}
8
+ {%- set tools = none %}
9
+ {%- endif %}
10
+ {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
+
12
+ {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
+ {%- set ns = namespace() %}
14
+ {%- set ns.index = 0 %}
15
+ {%- for message in loop_messages %}
16
+ {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
+ {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
+ {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
+ {%- endif %}
20
+ {%- set ns.index = ns.index + 1 %}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {{- bos_token }}
25
+ {%- for message in loop_messages %}
26
+ {%- if message["role"] == "user" %}
27
+ {%- if tools is not none and (message == user_messages[-1]) %}
28
+ {{- "[AVAILABLE_TOOLS][" }}
29
+ {%- for tool in tools %}
30
+ {%- set tool = tool.function %}
31
+ {{- '{"type": "function", "function": {' }}
32
+ {%- for key, val in tool.items() if key != "return" %}
33
+ {%- if val is string %}
34
+ {{- '"' + key + '": "' + val + '"' }}
35
+ {%- else %}
36
+ {{- '"' + key + '": ' + val|tojson }}
37
+ {%- endif %}
38
+ {%- if not loop.last %}
39
+ {{- ", " }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {{- "}}" }}
43
+ {%- if not loop.last %}
44
+ {{- ", " }}
45
+ {%- else %}
46
+ {{- "]" }}
47
+ {%- endif %}
48
+ {%- endfor %}
49
+ {{- "[/AVAILABLE_TOOLS]" }}
50
+ {%- endif %}
51
+ {%- if loop.last and system_message is defined %}
52
+ {{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
+ {%- else %}
54
+ {{- "[INST]" + message["content"] + "[/INST]" }}
55
+ {%- endif %}
56
+ {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
57
+ {{- "[TOOL_CALLS][" }}
58
+ {%- for tool_call in message.tool_calls %}
59
+ {%- set out = tool_call.function|tojson %}
60
+ {{- out[:-1] }}
61
+ {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
+ {%- endif %}
64
+ {{- ', "id": "' + tool_call.id + '"}' }}
65
+ {%- if not loop.last %}
66
+ {{- ", " }}
67
+ {%- else %}
68
+ {{- "]" + eos_token }}
69
+ {%- endif %}
70
+ {%- endfor %}
71
+ {%- elif message["role"] == "assistant" %}
72
+ {{- message["content"] + eos_token}}
73
+ {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
+ {%- if message.content is defined and message.content.content is defined %}
75
+ {%- set content = message.content.content %}
76
+ {%- else %}
77
+ {%- set content = message.content %}
78
+ {%- endif %}
79
+ {{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
80
+ {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
+ {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
82
+ {%- endif %}
83
+ {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
+ {%- else %}
85
+ {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
+ {%- endif %}
87
+ {%- endfor %}
config.json ADDED
@@ -0,0 +1,2292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 32,
20
+ "bits": 4,
21
+ "mode": "mxfp4",
22
+ "model.embed_tokens": {
23
+ "group_size": 32,
24
+ "bits": 4
25
+ },
26
+ "model.layers.0.self_attn.q_proj": {
27
+ "group_size": 32,
28
+ "bits": 4
29
+ },
30
+ "model.layers.0.self_attn.k_proj": {
31
+ "group_size": 32,
32
+ "bits": 4
33
+ },
34
+ "model.layers.0.self_attn.v_proj": {
35
+ "group_size": 32,
36
+ "bits": 6
37
+ },
38
+ "model.layers.0.self_attn.o_proj": {
39
+ "group_size": 32,
40
+ "bits": 4
41
+ },
42
+ "model.layers.0.mlp.gate_proj": {
43
+ "group_size": 32,
44
+ "bits": 4
45
+ },
46
+ "model.layers.0.mlp.down_proj": {
47
+ "group_size": 32,
48
+ "bits": 6
49
+ },
50
+ "model.layers.0.mlp.up_proj": {
51
+ "group_size": 32,
52
+ "bits": 4
53
+ },
54
+ "model.layers.1.self_attn.q_proj": {
55
+ "group_size": 32,
56
+ "bits": 4
57
+ },
58
+ "model.layers.1.self_attn.k_proj": {
59
+ "group_size": 32,
60
+ "bits": 4
61
+ },
62
+ "model.layers.1.self_attn.v_proj": {
63
+ "group_size": 32,
64
+ "bits": 6
65
+ },
66
+ "model.layers.1.self_attn.o_proj": {
67
+ "group_size": 32,
68
+ "bits": 4
69
+ },
70
+ "model.layers.1.mlp.gate_proj": {
71
+ "group_size": 32,
72
+ "bits": 4
73
+ },
74
+ "model.layers.1.mlp.down_proj": {
75
+ "group_size": 32,
76
+ "bits": 6
77
+ },
78
+ "model.layers.1.mlp.up_proj": {
79
+ "group_size": 32,
80
+ "bits": 4
81
+ },
82
+ "model.layers.2.self_attn.q_proj": {
83
+ "group_size": 32,
84
+ "bits": 4
85
+ },
86
+ "model.layers.2.self_attn.k_proj": {
87
+ "group_size": 32,
88
+ "bits": 4
89
+ },
90
+ "model.layers.2.self_attn.v_proj": {
91
+ "group_size": 32,
92
+ "bits": 6
93
+ },
94
+ "model.layers.2.self_attn.o_proj": {
95
+ "group_size": 32,
96
+ "bits": 4
97
+ },
98
+ "model.layers.2.mlp.gate_proj": {
99
+ "group_size": 32,
100
+ "bits": 4
101
+ },
102
+ "model.layers.2.mlp.down_proj": {
103
+ "group_size": 32,
104
+ "bits": 6
105
+ },
106
+ "model.layers.2.mlp.up_proj": {
107
+ "group_size": 32,
108
+ "bits": 4
109
+ },
110
+ "model.layers.3.self_attn.q_proj": {
111
+ "group_size": 32,
112
+ "bits": 4
113
+ },
114
+ "model.layers.3.self_attn.k_proj": {
115
+ "group_size": 32,
116
+ "bits": 4
117
+ },
118
+ "model.layers.3.self_attn.v_proj": {
119
+ "group_size": 32,
120
+ "bits": 6
121
+ },
122
+ "model.layers.3.self_attn.o_proj": {
123
+ "group_size": 32,
124
+ "bits": 4
125
+ },
126
+ "model.layers.3.mlp.gate_proj": {
127
+ "group_size": 32,
128
+ "bits": 4
129
+ },
130
+ "model.layers.3.mlp.down_proj": {
131
+ "group_size": 32,
132
+ "bits": 6
133
+ },
134
+ "model.layers.3.mlp.up_proj": {
135
+ "group_size": 32,
136
+ "bits": 4
137
+ },
138
+ "model.layers.4.self_attn.q_proj": {
139
+ "group_size": 32,
140
+ "bits": 4
141
+ },
142
+ "model.layers.4.self_attn.k_proj": {
143
+ "group_size": 32,
144
+ "bits": 4
145
+ },
146
+ "model.layers.4.self_attn.v_proj": {
147
+ "group_size": 32,
148
+ "bits": 6
149
+ },
150
+ "model.layers.4.self_attn.o_proj": {
151
+ "group_size": 32,
152
+ "bits": 4
153
+ },
154
+ "model.layers.4.mlp.gate_proj": {
155
+ "group_size": 32,
156
+ "bits": 4
157
+ },
158
+ "model.layers.4.mlp.down_proj": {
159
+ "group_size": 32,
160
+ "bits": 6
161
+ },
162
+ "model.layers.4.mlp.up_proj": {
163
+ "group_size": 32,
164
+ "bits": 4
165
+ },
166
+ "model.layers.5.self_attn.q_proj": {
167
+ "group_size": 32,
168
+ "bits": 4
169
+ },
170
+ "model.layers.5.self_attn.k_proj": {
171
+ "group_size": 32,
172
+ "bits": 4
173
+ },
174
+ "model.layers.5.self_attn.v_proj": {
175
+ "group_size": 32,
176
+ "bits": 4
177
+ },
178
+ "model.layers.5.self_attn.o_proj": {
179
+ "group_size": 32,
180
+ "bits": 4
181
+ },
182
+ "model.layers.5.mlp.gate_proj": {
183
+ "group_size": 32,
184
+ "bits": 4
185
+ },
186
+ "model.layers.5.mlp.down_proj": {
187
+ "group_size": 32,
188
+ "bits": 4
189
+ },
190
+ "model.layers.5.mlp.up_proj": {
191
+ "group_size": 32,
192
+ "bits": 4
193
+ },
194
+ "model.layers.6.self_attn.q_proj": {
195
+ "group_size": 32,
196
+ "bits": 4
197
+ },
198
+ "model.layers.6.self_attn.k_proj": {
199
+ "group_size": 32,
200
+ "bits": 4
201
+ },
202
+ "model.layers.6.self_attn.v_proj": {
203
+ "group_size": 32,
204
+ "bits": 4
205
+ },
206
+ "model.layers.6.self_attn.o_proj": {
207
+ "group_size": 32,
208
+ "bits": 4
209
+ },
210
+ "model.layers.6.mlp.gate_proj": {
211
+ "group_size": 32,
212
+ "bits": 4
213
+ },
214
+ "model.layers.6.mlp.down_proj": {
215
+ "group_size": 32,
216
+ "bits": 4
217
+ },
218
+ "model.layers.6.mlp.up_proj": {
219
+ "group_size": 32,
220
+ "bits": 4
221
+ },
222
+ "model.layers.7.self_attn.q_proj": {
223
+ "group_size": 32,
224
+ "bits": 4
225
+ },
226
+ "model.layers.7.self_attn.k_proj": {
227
+ "group_size": 32,
228
+ "bits": 4
229
+ },
230
+ "model.layers.7.self_attn.v_proj": {
231
+ "group_size": 32,
232
+ "bits": 6
233
+ },
234
+ "model.layers.7.self_attn.o_proj": {
235
+ "group_size": 32,
236
+ "bits": 4
237
+ },
238
+ "model.layers.7.mlp.gate_proj": {
239
+ "group_size": 32,
240
+ "bits": 4
241
+ },
242
+ "model.layers.7.mlp.down_proj": {
243
+ "group_size": 32,
244
+ "bits": 6
245
+ },
246
+ "model.layers.7.mlp.up_proj": {
247
+ "group_size": 32,
248
+ "bits": 4
249
+ },
250
+ "model.layers.8.self_attn.q_proj": {
251
+ "group_size": 32,
252
+ "bits": 4
253
+ },
254
+ "model.layers.8.self_attn.k_proj": {
255
+ "group_size": 32,
256
+ "bits": 4
257
+ },
258
+ "model.layers.8.self_attn.v_proj": {
259
+ "group_size": 32,
260
+ "bits": 4
261
+ },
262
+ "model.layers.8.self_attn.o_proj": {
263
+ "group_size": 32,
264
+ "bits": 4
265
+ },
266
+ "model.layers.8.mlp.gate_proj": {
267
+ "group_size": 32,
268
+ "bits": 4
269
+ },
270
+ "model.layers.8.mlp.down_proj": {
271
+ "group_size": 32,
272
+ "bits": 4
273
+ },
274
+ "model.layers.8.mlp.up_proj": {
275
+ "group_size": 32,
276
+ "bits": 4
277
+ },
278
+ "model.layers.9.self_attn.q_proj": {
279
+ "group_size": 32,
280
+ "bits": 4
281
+ },
282
+ "model.layers.9.self_attn.k_proj": {
283
+ "group_size": 32,
284
+ "bits": 4
285
+ },
286
+ "model.layers.9.self_attn.v_proj": {
287
+ "group_size": 32,
288
+ "bits": 4
289
+ },
290
+ "model.layers.9.self_attn.o_proj": {
291
+ "group_size": 32,
292
+ "bits": 4
293
+ },
294
+ "model.layers.9.mlp.gate_proj": {
295
+ "group_size": 32,
296
+ "bits": 4
297
+ },
298
+ "model.layers.9.mlp.down_proj": {
299
+ "group_size": 32,
300
+ "bits": 4
301
+ },
302
+ "model.layers.9.mlp.up_proj": {
303
+ "group_size": 32,
304
+ "bits": 4
305
+ },
306
+ "model.layers.10.self_attn.q_proj": {
307
+ "group_size": 32,
308
+ "bits": 4
309
+ },
310
+ "model.layers.10.self_attn.k_proj": {
311
+ "group_size": 32,
312
+ "bits": 4
313
+ },
314
+ "model.layers.10.self_attn.v_proj": {
315
+ "group_size": 32,
316
+ "bits": 6
317
+ },
318
+ "model.layers.10.self_attn.o_proj": {
319
+ "group_size": 32,
320
+ "bits": 4
321
+ },
322
+ "model.layers.10.mlp.gate_proj": {
323
+ "group_size": 32,
324
+ "bits": 4
325
+ },
326
+ "model.layers.10.mlp.down_proj": {
327
+ "group_size": 32,
328
+ "bits": 6
329
+ },
330
+ "model.layers.10.mlp.up_proj": {
331
+ "group_size": 32,
332
+ "bits": 4
333
+ },
334
+ "model.layers.11.self_attn.q_proj": {
335
+ "group_size": 32,
336
+ "bits": 4
337
+ },
338
+ "model.layers.11.self_attn.k_proj": {
339
+ "group_size": 32,
340
+ "bits": 4
341
+ },
342
+ "model.layers.11.self_attn.v_proj": {
343
+ "group_size": 32,
344
+ "bits": 4
345
+ },
346
+ "model.layers.11.self_attn.o_proj": {
347
+ "group_size": 32,
348
+ "bits": 4
349
+ },
350
+ "model.layers.11.mlp.gate_proj": {
351
+ "group_size": 32,
352
+ "bits": 4
353
+ },
354
+ "model.layers.11.mlp.down_proj": {
355
+ "group_size": 32,
356
+ "bits": 4
357
+ },
358
+ "model.layers.11.mlp.up_proj": {
359
+ "group_size": 32,
360
+ "bits": 4
361
+ },
362
+ "model.layers.12.self_attn.q_proj": {
363
+ "group_size": 32,
364
+ "bits": 4
365
+ },
366
+ "model.layers.12.self_attn.k_proj": {
367
+ "group_size": 32,
368
+ "bits": 4
369
+ },
370
+ "model.layers.12.self_attn.v_proj": {
371
+ "group_size": 32,
372
+ "bits": 4
373
+ },
374
+ "model.layers.12.self_attn.o_proj": {
375
+ "group_size": 32,
376
+ "bits": 4
377
+ },
378
+ "model.layers.12.mlp.gate_proj": {
379
+ "group_size": 32,
380
+ "bits": 4
381
+ },
382
+ "model.layers.12.mlp.down_proj": {
383
+ "group_size": 32,
384
+ "bits": 4
385
+ },
386
+ "model.layers.12.mlp.up_proj": {
387
+ "group_size": 32,
388
+ "bits": 4
389
+ },
390
+ "model.layers.13.self_attn.q_proj": {
391
+ "group_size": 32,
392
+ "bits": 4
393
+ },
394
+ "model.layers.13.self_attn.k_proj": {
395
+ "group_size": 32,
396
+ "bits": 4
397
+ },
398
+ "model.layers.13.self_attn.v_proj": {
399
+ "group_size": 32,
400
+ "bits": 6
401
+ },
402
+ "model.layers.13.self_attn.o_proj": {
403
+ "group_size": 32,
404
+ "bits": 4
405
+ },
406
+ "model.layers.13.mlp.gate_proj": {
407
+ "group_size": 32,
408
+ "bits": 4
409
+ },
410
+ "model.layers.13.mlp.down_proj": {
411
+ "group_size": 32,
412
+ "bits": 6
413
+ },
414
+ "model.layers.13.mlp.up_proj": {
415
+ "group_size": 32,
416
+ "bits": 4
417
+ },
418
+ "model.layers.14.self_attn.q_proj": {
419
+ "group_size": 32,
420
+ "bits": 4
421
+ },
422
+ "model.layers.14.self_attn.k_proj": {
423
+ "group_size": 32,
424
+ "bits": 4
425
+ },
426
+ "model.layers.14.self_attn.v_proj": {
427
+ "group_size": 32,
428
+ "bits": 4
429
+ },
430
+ "model.layers.14.self_attn.o_proj": {
431
+ "group_size": 32,
432
+ "bits": 4
433
+ },
434
+ "model.layers.14.mlp.gate_proj": {
435
+ "group_size": 32,
436
+ "bits": 4
437
+ },
438
+ "model.layers.14.mlp.down_proj": {
439
+ "group_size": 32,
440
+ "bits": 4
441
+ },
442
+ "model.layers.14.mlp.up_proj": {
443
+ "group_size": 32,
444
+ "bits": 4
445
+ },
446
+ "model.layers.15.self_attn.q_proj": {
447
+ "group_size": 32,
448
+ "bits": 4
449
+ },
450
+ "model.layers.15.self_attn.k_proj": {
451
+ "group_size": 32,
452
+ "bits": 4
453
+ },
454
+ "model.layers.15.self_attn.v_proj": {
455
+ "group_size": 32,
456
+ "bits": 4
457
+ },
458
+ "model.layers.15.self_attn.o_proj": {
459
+ "group_size": 32,
460
+ "bits": 4
461
+ },
462
+ "model.layers.15.mlp.gate_proj": {
463
+ "group_size": 32,
464
+ "bits": 4
465
+ },
466
+ "model.layers.15.mlp.down_proj": {
467
+ "group_size": 32,
468
+ "bits": 4
469
+ },
470
+ "model.layers.15.mlp.up_proj": {
471
+ "group_size": 32,
472
+ "bits": 4
473
+ },
474
+ "model.layers.16.self_attn.q_proj": {
475
+ "group_size": 32,
476
+ "bits": 4
477
+ },
478
+ "model.layers.16.self_attn.k_proj": {
479
+ "group_size": 32,
480
+ "bits": 4
481
+ },
482
+ "model.layers.16.self_attn.v_proj": {
483
+ "group_size": 32,
484
+ "bits": 6
485
+ },
486
+ "model.layers.16.self_attn.o_proj": {
487
+ "group_size": 32,
488
+ "bits": 4
489
+ },
490
+ "model.layers.16.mlp.gate_proj": {
491
+ "group_size": 32,
492
+ "bits": 4
493
+ },
494
+ "model.layers.16.mlp.down_proj": {
495
+ "group_size": 32,
496
+ "bits": 6
497
+ },
498
+ "model.layers.16.mlp.up_proj": {
499
+ "group_size": 32,
500
+ "bits": 4
501
+ },
502
+ "model.layers.17.self_attn.q_proj": {
503
+ "group_size": 32,
504
+ "bits": 4
505
+ },
506
+ "model.layers.17.self_attn.k_proj": {
507
+ "group_size": 32,
508
+ "bits": 4
509
+ },
510
+ "model.layers.17.self_attn.v_proj": {
511
+ "group_size": 32,
512
+ "bits": 4
513
+ },
514
+ "model.layers.17.self_attn.o_proj": {
515
+ "group_size": 32,
516
+ "bits": 4
517
+ },
518
+ "model.layers.17.mlp.gate_proj": {
519
+ "group_size": 32,
520
+ "bits": 4
521
+ },
522
+ "model.layers.17.mlp.down_proj": {
523
+ "group_size": 32,
524
+ "bits": 4
525
+ },
526
+ "model.layers.17.mlp.up_proj": {
527
+ "group_size": 32,
528
+ "bits": 4
529
+ },
530
+ "model.layers.18.self_attn.q_proj": {
531
+ "group_size": 32,
532
+ "bits": 4
533
+ },
534
+ "model.layers.18.self_attn.k_proj": {
535
+ "group_size": 32,
536
+ "bits": 4
537
+ },
538
+ "model.layers.18.self_attn.v_proj": {
539
+ "group_size": 32,
540
+ "bits": 4
541
+ },
542
+ "model.layers.18.self_attn.o_proj": {
543
+ "group_size": 32,
544
+ "bits": 4
545
+ },
546
+ "model.layers.18.mlp.gate_proj": {
547
+ "group_size": 32,
548
+ "bits": 4
549
+ },
550
+ "model.layers.18.mlp.down_proj": {
551
+ "group_size": 32,
552
+ "bits": 4
553
+ },
554
+ "model.layers.18.mlp.up_proj": {
555
+ "group_size": 32,
556
+ "bits": 4
557
+ },
558
+ "model.layers.19.self_attn.q_proj": {
559
+ "group_size": 32,
560
+ "bits": 4
561
+ },
562
+ "model.layers.19.self_attn.k_proj": {
563
+ "group_size": 32,
564
+ "bits": 4
565
+ },
566
+ "model.layers.19.self_attn.v_proj": {
567
+ "group_size": 32,
568
+ "bits": 6
569
+ },
570
+ "model.layers.19.self_attn.o_proj": {
571
+ "group_size": 32,
572
+ "bits": 4
573
+ },
574
+ "model.layers.19.mlp.gate_proj": {
575
+ "group_size": 32,
576
+ "bits": 4
577
+ },
578
+ "model.layers.19.mlp.down_proj": {
579
+ "group_size": 32,
580
+ "bits": 6
581
+ },
582
+ "model.layers.19.mlp.up_proj": {
583
+ "group_size": 32,
584
+ "bits": 4
585
+ },
586
+ "model.layers.20.self_attn.q_proj": {
587
+ "group_size": 32,
588
+ "bits": 4
589
+ },
590
+ "model.layers.20.self_attn.k_proj": {
591
+ "group_size": 32,
592
+ "bits": 4
593
+ },
594
+ "model.layers.20.self_attn.v_proj": {
595
+ "group_size": 32,
596
+ "bits": 4
597
+ },
598
+ "model.layers.20.self_attn.o_proj": {
599
+ "group_size": 32,
600
+ "bits": 4
601
+ },
602
+ "model.layers.20.mlp.gate_proj": {
603
+ "group_size": 32,
604
+ "bits": 4
605
+ },
606
+ "model.layers.20.mlp.down_proj": {
607
+ "group_size": 32,
608
+ "bits": 4
609
+ },
610
+ "model.layers.20.mlp.up_proj": {
611
+ "group_size": 32,
612
+ "bits": 4
613
+ },
614
+ "model.layers.21.self_attn.q_proj": {
615
+ "group_size": 32,
616
+ "bits": 4
617
+ },
618
+ "model.layers.21.self_attn.k_proj": {
619
+ "group_size": 32,
620
+ "bits": 4
621
+ },
622
+ "model.layers.21.self_attn.v_proj": {
623
+ "group_size": 32,
624
+ "bits": 4
625
+ },
626
+ "model.layers.21.self_attn.o_proj": {
627
+ "group_size": 32,
628
+ "bits": 4
629
+ },
630
+ "model.layers.21.mlp.gate_proj": {
631
+ "group_size": 32,
632
+ "bits": 4
633
+ },
634
+ "model.layers.21.mlp.down_proj": {
635
+ "group_size": 32,
636
+ "bits": 4
637
+ },
638
+ "model.layers.21.mlp.up_proj": {
639
+ "group_size": 32,
640
+ "bits": 4
641
+ },
642
+ "model.layers.22.self_attn.q_proj": {
643
+ "group_size": 32,
644
+ "bits": 4
645
+ },
646
+ "model.layers.22.self_attn.k_proj": {
647
+ "group_size": 32,
648
+ "bits": 4
649
+ },
650
+ "model.layers.22.self_attn.v_proj": {
651
+ "group_size": 32,
652
+ "bits": 6
653
+ },
654
+ "model.layers.22.self_attn.o_proj": {
655
+ "group_size": 32,
656
+ "bits": 4
657
+ },
658
+ "model.layers.22.mlp.gate_proj": {
659
+ "group_size": 32,
660
+ "bits": 4
661
+ },
662
+ "model.layers.22.mlp.down_proj": {
663
+ "group_size": 32,
664
+ "bits": 6
665
+ },
666
+ "model.layers.22.mlp.up_proj": {
667
+ "group_size": 32,
668
+ "bits": 4
669
+ },
670
+ "model.layers.23.self_attn.q_proj": {
671
+ "group_size": 32,
672
+ "bits": 4
673
+ },
674
+ "model.layers.23.self_attn.k_proj": {
675
+ "group_size": 32,
676
+ "bits": 4
677
+ },
678
+ "model.layers.23.self_attn.v_proj": {
679
+ "group_size": 32,
680
+ "bits": 4
681
+ },
682
+ "model.layers.23.self_attn.o_proj": {
683
+ "group_size": 32,
684
+ "bits": 4
685
+ },
686
+ "model.layers.23.mlp.gate_proj": {
687
+ "group_size": 32,
688
+ "bits": 4
689
+ },
690
+ "model.layers.23.mlp.down_proj": {
691
+ "group_size": 32,
692
+ "bits": 4
693
+ },
694
+ "model.layers.23.mlp.up_proj": {
695
+ "group_size": 32,
696
+ "bits": 4
697
+ },
698
+ "model.layers.24.self_attn.q_proj": {
699
+ "group_size": 32,
700
+ "bits": 4
701
+ },
702
+ "model.layers.24.self_attn.k_proj": {
703
+ "group_size": 32,
704
+ "bits": 4
705
+ },
706
+ "model.layers.24.self_attn.v_proj": {
707
+ "group_size": 32,
708
+ "bits": 4
709
+ },
710
+ "model.layers.24.self_attn.o_proj": {
711
+ "group_size": 32,
712
+ "bits": 4
713
+ },
714
+ "model.layers.24.mlp.gate_proj": {
715
+ "group_size": 32,
716
+ "bits": 4
717
+ },
718
+ "model.layers.24.mlp.down_proj": {
719
+ "group_size": 32,
720
+ "bits": 4
721
+ },
722
+ "model.layers.24.mlp.up_proj": {
723
+ "group_size": 32,
724
+ "bits": 4
725
+ },
726
+ "model.layers.25.self_attn.q_proj": {
727
+ "group_size": 32,
728
+ "bits": 4
729
+ },
730
+ "model.layers.25.self_attn.k_proj": {
731
+ "group_size": 32,
732
+ "bits": 4
733
+ },
734
+ "model.layers.25.self_attn.v_proj": {
735
+ "group_size": 32,
736
+ "bits": 6
737
+ },
738
+ "model.layers.25.self_attn.o_proj": {
739
+ "group_size": 32,
740
+ "bits": 4
741
+ },
742
+ "model.layers.25.mlp.gate_proj": {
743
+ "group_size": 32,
744
+ "bits": 4
745
+ },
746
+ "model.layers.25.mlp.down_proj": {
747
+ "group_size": 32,
748
+ "bits": 6
749
+ },
750
+ "model.layers.25.mlp.up_proj": {
751
+ "group_size": 32,
752
+ "bits": 4
753
+ },
754
+ "model.layers.26.self_attn.q_proj": {
755
+ "group_size": 32,
756
+ "bits": 4
757
+ },
758
+ "model.layers.26.self_attn.k_proj": {
759
+ "group_size": 32,
760
+ "bits": 4
761
+ },
762
+ "model.layers.26.self_attn.v_proj": {
763
+ "group_size": 32,
764
+ "bits": 4
765
+ },
766
+ "model.layers.26.self_attn.o_proj": {
767
+ "group_size": 32,
768
+ "bits": 4
769
+ },
770
+ "model.layers.26.mlp.gate_proj": {
771
+ "group_size": 32,
772
+ "bits": 4
773
+ },
774
+ "model.layers.26.mlp.down_proj": {
775
+ "group_size": 32,
776
+ "bits": 4
777
+ },
778
+ "model.layers.26.mlp.up_proj": {
779
+ "group_size": 32,
780
+ "bits": 4
781
+ },
782
+ "model.layers.27.self_attn.q_proj": {
783
+ "group_size": 32,
784
+ "bits": 4
785
+ },
786
+ "model.layers.27.self_attn.k_proj": {
787
+ "group_size": 32,
788
+ "bits": 4
789
+ },
790
+ "model.layers.27.self_attn.v_proj": {
791
+ "group_size": 32,
792
+ "bits": 4
793
+ },
794
+ "model.layers.27.self_attn.o_proj": {
795
+ "group_size": 32,
796
+ "bits": 4
797
+ },
798
+ "model.layers.27.mlp.gate_proj": {
799
+ "group_size": 32,
800
+ "bits": 4
801
+ },
802
+ "model.layers.27.mlp.down_proj": {
803
+ "group_size": 32,
804
+ "bits": 4
805
+ },
806
+ "model.layers.27.mlp.up_proj": {
807
+ "group_size": 32,
808
+ "bits": 4
809
+ },
810
+ "model.layers.28.self_attn.q_proj": {
811
+ "group_size": 32,
812
+ "bits": 4
813
+ },
814
+ "model.layers.28.self_attn.k_proj": {
815
+ "group_size": 32,
816
+ "bits": 4
817
+ },
818
+ "model.layers.28.self_attn.v_proj": {
819
+ "group_size": 32,
820
+ "bits": 6
821
+ },
822
+ "model.layers.28.self_attn.o_proj": {
823
+ "group_size": 32,
824
+ "bits": 4
825
+ },
826
+ "model.layers.28.mlp.gate_proj": {
827
+ "group_size": 32,
828
+ "bits": 4
829
+ },
830
+ "model.layers.28.mlp.down_proj": {
831
+ "group_size": 32,
832
+ "bits": 6
833
+ },
834
+ "model.layers.28.mlp.up_proj": {
835
+ "group_size": 32,
836
+ "bits": 4
837
+ },
838
+ "model.layers.29.self_attn.q_proj": {
839
+ "group_size": 32,
840
+ "bits": 4
841
+ },
842
+ "model.layers.29.self_attn.k_proj": {
843
+ "group_size": 32,
844
+ "bits": 4
845
+ },
846
+ "model.layers.29.self_attn.v_proj": {
847
+ "group_size": 32,
848
+ "bits": 4
849
+ },
850
+ "model.layers.29.self_attn.o_proj": {
851
+ "group_size": 32,
852
+ "bits": 4
853
+ },
854
+ "model.layers.29.mlp.gate_proj": {
855
+ "group_size": 32,
856
+ "bits": 4
857
+ },
858
+ "model.layers.29.mlp.down_proj": {
859
+ "group_size": 32,
860
+ "bits": 4
861
+ },
862
+ "model.layers.29.mlp.up_proj": {
863
+ "group_size": 32,
864
+ "bits": 4
865
+ },
866
+ "model.layers.30.self_attn.q_proj": {
867
+ "group_size": 32,
868
+ "bits": 4
869
+ },
870
+ "model.layers.30.self_attn.k_proj": {
871
+ "group_size": 32,
872
+ "bits": 4
873
+ },
874
+ "model.layers.30.self_attn.v_proj": {
875
+ "group_size": 32,
876
+ "bits": 4
877
+ },
878
+ "model.layers.30.self_attn.o_proj": {
879
+ "group_size": 32,
880
+ "bits": 4
881
+ },
882
+ "model.layers.30.mlp.gate_proj": {
883
+ "group_size": 32,
884
+ "bits": 4
885
+ },
886
+ "model.layers.30.mlp.down_proj": {
887
+ "group_size": 32,
888
+ "bits": 4
889
+ },
890
+ "model.layers.30.mlp.up_proj": {
891
+ "group_size": 32,
892
+ "bits": 4
893
+ },
894
+ "model.layers.31.self_attn.q_proj": {
895
+ "group_size": 32,
896
+ "bits": 4
897
+ },
898
+ "model.layers.31.self_attn.k_proj": {
899
+ "group_size": 32,
900
+ "bits": 4
901
+ },
902
+ "model.layers.31.self_attn.v_proj": {
903
+ "group_size": 32,
904
+ "bits": 6
905
+ },
906
+ "model.layers.31.self_attn.o_proj": {
907
+ "group_size": 32,
908
+ "bits": 4
909
+ },
910
+ "model.layers.31.mlp.gate_proj": {
911
+ "group_size": 32,
912
+ "bits": 4
913
+ },
914
+ "model.layers.31.mlp.down_proj": {
915
+ "group_size": 32,
916
+ "bits": 6
917
+ },
918
+ "model.layers.31.mlp.up_proj": {
919
+ "group_size": 32,
920
+ "bits": 4
921
+ },
922
+ "model.layers.32.self_attn.q_proj": {
923
+ "group_size": 32,
924
+ "bits": 4
925
+ },
926
+ "model.layers.32.self_attn.k_proj": {
927
+ "group_size": 32,
928
+ "bits": 4
929
+ },
930
+ "model.layers.32.self_attn.v_proj": {
931
+ "group_size": 32,
932
+ "bits": 4
933
+ },
934
+ "model.layers.32.self_attn.o_proj": {
935
+ "group_size": 32,
936
+ "bits": 4
937
+ },
938
+ "model.layers.32.mlp.gate_proj": {
939
+ "group_size": 32,
940
+ "bits": 4
941
+ },
942
+ "model.layers.32.mlp.down_proj": {
943
+ "group_size": 32,
944
+ "bits": 4
945
+ },
946
+ "model.layers.32.mlp.up_proj": {
947
+ "group_size": 32,
948
+ "bits": 4
949
+ },
950
+ "model.layers.33.self_attn.q_proj": {
951
+ "group_size": 32,
952
+ "bits": 4
953
+ },
954
+ "model.layers.33.self_attn.k_proj": {
955
+ "group_size": 32,
956
+ "bits": 4
957
+ },
958
+ "model.layers.33.self_attn.v_proj": {
959
+ "group_size": 32,
960
+ "bits": 4
961
+ },
962
+ "model.layers.33.self_attn.o_proj": {
963
+ "group_size": 32,
964
+ "bits": 4
965
+ },
966
+ "model.layers.33.mlp.gate_proj": {
967
+ "group_size": 32,
968
+ "bits": 4
969
+ },
970
+ "model.layers.33.mlp.down_proj": {
971
+ "group_size": 32,
972
+ "bits": 4
973
+ },
974
+ "model.layers.33.mlp.up_proj": {
975
+ "group_size": 32,
976
+ "bits": 4
977
+ },
978
+ "model.layers.34.self_attn.q_proj": {
979
+ "group_size": 32,
980
+ "bits": 4
981
+ },
982
+ "model.layers.34.self_attn.k_proj": {
983
+ "group_size": 32,
984
+ "bits": 4
985
+ },
986
+ "model.layers.34.self_attn.v_proj": {
987
+ "group_size": 32,
988
+ "bits": 6
989
+ },
990
+ "model.layers.34.self_attn.o_proj": {
991
+ "group_size": 32,
992
+ "bits": 4
993
+ },
994
+ "model.layers.34.mlp.gate_proj": {
995
+ "group_size": 32,
996
+ "bits": 4
997
+ },
998
+ "model.layers.34.mlp.down_proj": {
999
+ "group_size": 32,
1000
+ "bits": 6
1001
+ },
1002
+ "model.layers.34.mlp.up_proj": {
1003
+ "group_size": 32,
1004
+ "bits": 4
1005
+ },
1006
+ "model.layers.35.self_attn.q_proj": {
1007
+ "group_size": 32,
1008
+ "bits": 4
1009
+ },
1010
+ "model.layers.35.self_attn.k_proj": {
1011
+ "group_size": 32,
1012
+ "bits": 4
1013
+ },
1014
+ "model.layers.35.self_attn.v_proj": {
1015
+ "group_size": 32,
1016
+ "bits": 6
1017
+ },
1018
+ "model.layers.35.self_attn.o_proj": {
1019
+ "group_size": 32,
1020
+ "bits": 4
1021
+ },
1022
+ "model.layers.35.mlp.gate_proj": {
1023
+ "group_size": 32,
1024
+ "bits": 4
1025
+ },
1026
+ "model.layers.35.mlp.down_proj": {
1027
+ "group_size": 32,
1028
+ "bits": 6
1029
+ },
1030
+ "model.layers.35.mlp.up_proj": {
1031
+ "group_size": 32,
1032
+ "bits": 4
1033
+ },
1034
+ "model.layers.36.self_attn.q_proj": {
1035
+ "group_size": 32,
1036
+ "bits": 4
1037
+ },
1038
+ "model.layers.36.self_attn.k_proj": {
1039
+ "group_size": 32,
1040
+ "bits": 4
1041
+ },
1042
+ "model.layers.36.self_attn.v_proj": {
1043
+ "group_size": 32,
1044
+ "bits": 6
1045
+ },
1046
+ "model.layers.36.self_attn.o_proj": {
1047
+ "group_size": 32,
1048
+ "bits": 4
1049
+ },
1050
+ "model.layers.36.mlp.gate_proj": {
1051
+ "group_size": 32,
1052
+ "bits": 4
1053
+ },
1054
+ "model.layers.36.mlp.down_proj": {
1055
+ "group_size": 32,
1056
+ "bits": 6
1057
+ },
1058
+ "model.layers.36.mlp.up_proj": {
1059
+ "group_size": 32,
1060
+ "bits": 4
1061
+ },
1062
+ "model.layers.37.self_attn.q_proj": {
1063
+ "group_size": 32,
1064
+ "bits": 4
1065
+ },
1066
+ "model.layers.37.self_attn.k_proj": {
1067
+ "group_size": 32,
1068
+ "bits": 4
1069
+ },
1070
+ "model.layers.37.self_attn.v_proj": {
1071
+ "group_size": 32,
1072
+ "bits": 6
1073
+ },
1074
+ "model.layers.37.self_attn.o_proj": {
1075
+ "group_size": 32,
1076
+ "bits": 4
1077
+ },
1078
+ "model.layers.37.mlp.gate_proj": {
1079
+ "group_size": 32,
1080
+ "bits": 4
1081
+ },
1082
+ "model.layers.37.mlp.down_proj": {
1083
+ "group_size": 32,
1084
+ "bits": 6
1085
+ },
1086
+ "model.layers.37.mlp.up_proj": {
1087
+ "group_size": 32,
1088
+ "bits": 4
1089
+ },
1090
+ "model.layers.38.self_attn.q_proj": {
1091
+ "group_size": 32,
1092
+ "bits": 4
1093
+ },
1094
+ "model.layers.38.self_attn.k_proj": {
1095
+ "group_size": 32,
1096
+ "bits": 4
1097
+ },
1098
+ "model.layers.38.self_attn.v_proj": {
1099
+ "group_size": 32,
1100
+ "bits": 6
1101
+ },
1102
+ "model.layers.38.self_attn.o_proj": {
1103
+ "group_size": 32,
1104
+ "bits": 4
1105
+ },
1106
+ "model.layers.38.mlp.gate_proj": {
1107
+ "group_size": 32,
1108
+ "bits": 4
1109
+ },
1110
+ "model.layers.38.mlp.down_proj": {
1111
+ "group_size": 32,
1112
+ "bits": 6
1113
+ },
1114
+ "model.layers.38.mlp.up_proj": {
1115
+ "group_size": 32,
1116
+ "bits": 4
1117
+ },
1118
+ "model.layers.39.self_attn.q_proj": {
1119
+ "group_size": 32,
1120
+ "bits": 4
1121
+ },
1122
+ "model.layers.39.self_attn.k_proj": {
1123
+ "group_size": 32,
1124
+ "bits": 4
1125
+ },
1126
+ "model.layers.39.self_attn.v_proj": {
1127
+ "group_size": 32,
1128
+ "bits": 6
1129
+ },
1130
+ "model.layers.39.self_attn.o_proj": {
1131
+ "group_size": 32,
1132
+ "bits": 4
1133
+ },
1134
+ "model.layers.39.mlp.gate_proj": {
1135
+ "group_size": 32,
1136
+ "bits": 4
1137
+ },
1138
+ "model.layers.39.mlp.down_proj": {
1139
+ "group_size": 32,
1140
+ "bits": 6
1141
+ },
1142
+ "model.layers.39.mlp.up_proj": {
1143
+ "group_size": 32,
1144
+ "bits": 4
1145
+ },
1146
+ "lm_head": {
1147
+ "group_size": 32,
1148
+ "bits": 6
1149
+ }
1150
+ },
1151
+ "quantization_config": {
1152
+ "group_size": 32,
1153
+ "bits": 4,
1154
+ "mode": "mxfp4",
1155
+ "model.embed_tokens": {
1156
+ "group_size": 32,
1157
+ "bits": 4
1158
+ },
1159
+ "model.layers.0.self_attn.q_proj": {
1160
+ "group_size": 32,
1161
+ "bits": 4
1162
+ },
1163
+ "model.layers.0.self_attn.k_proj": {
1164
+ "group_size": 32,
1165
+ "bits": 4
1166
+ },
1167
+ "model.layers.0.self_attn.v_proj": {
1168
+ "group_size": 32,
1169
+ "bits": 6
1170
+ },
1171
+ "model.layers.0.self_attn.o_proj": {
1172
+ "group_size": 32,
1173
+ "bits": 4
1174
+ },
1175
+ "model.layers.0.mlp.gate_proj": {
1176
+ "group_size": 32,
1177
+ "bits": 4
1178
+ },
1179
+ "model.layers.0.mlp.down_proj": {
1180
+ "group_size": 32,
1181
+ "bits": 6
1182
+ },
1183
+ "model.layers.0.mlp.up_proj": {
1184
+ "group_size": 32,
1185
+ "bits": 4
1186
+ },
1187
+ "model.layers.1.self_attn.q_proj": {
1188
+ "group_size": 32,
1189
+ "bits": 4
1190
+ },
1191
+ "model.layers.1.self_attn.k_proj": {
1192
+ "group_size": 32,
1193
+ "bits": 4
1194
+ },
1195
+ "model.layers.1.self_attn.v_proj": {
1196
+ "group_size": 32,
1197
+ "bits": 6
1198
+ },
1199
+ "model.layers.1.self_attn.o_proj": {
1200
+ "group_size": 32,
1201
+ "bits": 4
1202
+ },
1203
+ "model.layers.1.mlp.gate_proj": {
1204
+ "group_size": 32,
1205
+ "bits": 4
1206
+ },
1207
+ "model.layers.1.mlp.down_proj": {
1208
+ "group_size": 32,
1209
+ "bits": 6
1210
+ },
1211
+ "model.layers.1.mlp.up_proj": {
1212
+ "group_size": 32,
1213
+ "bits": 4
1214
+ },
1215
+ "model.layers.2.self_attn.q_proj": {
1216
+ "group_size": 32,
1217
+ "bits": 4
1218
+ },
1219
+ "model.layers.2.self_attn.k_proj": {
1220
+ "group_size": 32,
1221
+ "bits": 4
1222
+ },
1223
+ "model.layers.2.self_attn.v_proj": {
1224
+ "group_size": 32,
1225
+ "bits": 6
1226
+ },
1227
+ "model.layers.2.self_attn.o_proj": {
1228
+ "group_size": 32,
1229
+ "bits": 4
1230
+ },
1231
+ "model.layers.2.mlp.gate_proj": {
1232
+ "group_size": 32,
1233
+ "bits": 4
1234
+ },
1235
+ "model.layers.2.mlp.down_proj": {
1236
+ "group_size": 32,
1237
+ "bits": 6
1238
+ },
1239
+ "model.layers.2.mlp.up_proj": {
1240
+ "group_size": 32,
1241
+ "bits": 4
1242
+ },
1243
+ "model.layers.3.self_attn.q_proj": {
1244
+ "group_size": 32,
1245
+ "bits": 4
1246
+ },
1247
+ "model.layers.3.self_attn.k_proj": {
1248
+ "group_size": 32,
1249
+ "bits": 4
1250
+ },
1251
+ "model.layers.3.self_attn.v_proj": {
1252
+ "group_size": 32,
1253
+ "bits": 6
1254
+ },
1255
+ "model.layers.3.self_attn.o_proj": {
1256
+ "group_size": 32,
1257
+ "bits": 4
1258
+ },
1259
+ "model.layers.3.mlp.gate_proj": {
1260
+ "group_size": 32,
1261
+ "bits": 4
1262
+ },
1263
+ "model.layers.3.mlp.down_proj": {
1264
+ "group_size": 32,
1265
+ "bits": 6
1266
+ },
1267
+ "model.layers.3.mlp.up_proj": {
1268
+ "group_size": 32,
1269
+ "bits": 4
1270
+ },
1271
+ "model.layers.4.self_attn.q_proj": {
1272
+ "group_size": 32,
1273
+ "bits": 4
1274
+ },
1275
+ "model.layers.4.self_attn.k_proj": {
1276
+ "group_size": 32,
1277
+ "bits": 4
1278
+ },
1279
+ "model.layers.4.self_attn.v_proj": {
1280
+ "group_size": 32,
1281
+ "bits": 6
1282
+ },
1283
+ "model.layers.4.self_attn.o_proj": {
1284
+ "group_size": 32,
1285
+ "bits": 4
1286
+ },
1287
+ "model.layers.4.mlp.gate_proj": {
1288
+ "group_size": 32,
1289
+ "bits": 4
1290
+ },
1291
+ "model.layers.4.mlp.down_proj": {
1292
+ "group_size": 32,
1293
+ "bits": 6
1294
+ },
1295
+ "model.layers.4.mlp.up_proj": {
1296
+ "group_size": 32,
1297
+ "bits": 4
1298
+ },
1299
+ "model.layers.5.self_attn.q_proj": {
1300
+ "group_size": 32,
1301
+ "bits": 4
1302
+ },
1303
+ "model.layers.5.self_attn.k_proj": {
1304
+ "group_size": 32,
1305
+ "bits": 4
1306
+ },
1307
+ "model.layers.5.self_attn.v_proj": {
1308
+ "group_size": 32,
1309
+ "bits": 4
1310
+ },
1311
+ "model.layers.5.self_attn.o_proj": {
1312
+ "group_size": 32,
1313
+ "bits": 4
1314
+ },
1315
+ "model.layers.5.mlp.gate_proj": {
1316
+ "group_size": 32,
1317
+ "bits": 4
1318
+ },
1319
+ "model.layers.5.mlp.down_proj": {
1320
+ "group_size": 32,
1321
+ "bits": 4
1322
+ },
1323
+ "model.layers.5.mlp.up_proj": {
1324
+ "group_size": 32,
1325
+ "bits": 4
1326
+ },
1327
+ "model.layers.6.self_attn.q_proj": {
1328
+ "group_size": 32,
1329
+ "bits": 4
1330
+ },
1331
+ "model.layers.6.self_attn.k_proj": {
1332
+ "group_size": 32,
1333
+ "bits": 4
1334
+ },
1335
+ "model.layers.6.self_attn.v_proj": {
1336
+ "group_size": 32,
1337
+ "bits": 4
1338
+ },
1339
+ "model.layers.6.self_attn.o_proj": {
1340
+ "group_size": 32,
1341
+ "bits": 4
1342
+ },
1343
+ "model.layers.6.mlp.gate_proj": {
1344
+ "group_size": 32,
1345
+ "bits": 4
1346
+ },
1347
+ "model.layers.6.mlp.down_proj": {
1348
+ "group_size": 32,
1349
+ "bits": 4
1350
+ },
1351
+ "model.layers.6.mlp.up_proj": {
1352
+ "group_size": 32,
1353
+ "bits": 4
1354
+ },
1355
+ "model.layers.7.self_attn.q_proj": {
1356
+ "group_size": 32,
1357
+ "bits": 4
1358
+ },
1359
+ "model.layers.7.self_attn.k_proj": {
1360
+ "group_size": 32,
1361
+ "bits": 4
1362
+ },
1363
+ "model.layers.7.self_attn.v_proj": {
1364
+ "group_size": 32,
1365
+ "bits": 6
1366
+ },
1367
+ "model.layers.7.self_attn.o_proj": {
1368
+ "group_size": 32,
1369
+ "bits": 4
1370
+ },
1371
+ "model.layers.7.mlp.gate_proj": {
1372
+ "group_size": 32,
1373
+ "bits": 4
1374
+ },
1375
+ "model.layers.7.mlp.down_proj": {
1376
+ "group_size": 32,
1377
+ "bits": 6
1378
+ },
1379
+ "model.layers.7.mlp.up_proj": {
1380
+ "group_size": 32,
1381
+ "bits": 4
1382
+ },
1383
+ "model.layers.8.self_attn.q_proj": {
1384
+ "group_size": 32,
1385
+ "bits": 4
1386
+ },
1387
+ "model.layers.8.self_attn.k_proj": {
1388
+ "group_size": 32,
1389
+ "bits": 4
1390
+ },
1391
+ "model.layers.8.self_attn.v_proj": {
1392
+ "group_size": 32,
1393
+ "bits": 4
1394
+ },
1395
+ "model.layers.8.self_attn.o_proj": {
1396
+ "group_size": 32,
1397
+ "bits": 4
1398
+ },
1399
+ "model.layers.8.mlp.gate_proj": {
1400
+ "group_size": 32,
1401
+ "bits": 4
1402
+ },
1403
+ "model.layers.8.mlp.down_proj": {
1404
+ "group_size": 32,
1405
+ "bits": 4
1406
+ },
1407
+ "model.layers.8.mlp.up_proj": {
1408
+ "group_size": 32,
1409
+ "bits": 4
1410
+ },
1411
+ "model.layers.9.self_attn.q_proj": {
1412
+ "group_size": 32,
1413
+ "bits": 4
1414
+ },
1415
+ "model.layers.9.self_attn.k_proj": {
1416
+ "group_size": 32,
1417
+ "bits": 4
1418
+ },
1419
+ "model.layers.9.self_attn.v_proj": {
1420
+ "group_size": 32,
1421
+ "bits": 4
1422
+ },
1423
+ "model.layers.9.self_attn.o_proj": {
1424
+ "group_size": 32,
1425
+ "bits": 4
1426
+ },
1427
+ "model.layers.9.mlp.gate_proj": {
1428
+ "group_size": 32,
1429
+ "bits": 4
1430
+ },
1431
+ "model.layers.9.mlp.down_proj": {
1432
+ "group_size": 32,
1433
+ "bits": 4
1434
+ },
1435
+ "model.layers.9.mlp.up_proj": {
1436
+ "group_size": 32,
1437
+ "bits": 4
1438
+ },
1439
+ "model.layers.10.self_attn.q_proj": {
1440
+ "group_size": 32,
1441
+ "bits": 4
1442
+ },
1443
+ "model.layers.10.self_attn.k_proj": {
1444
+ "group_size": 32,
1445
+ "bits": 4
1446
+ },
1447
+ "model.layers.10.self_attn.v_proj": {
1448
+ "group_size": 32,
1449
+ "bits": 6
1450
+ },
1451
+ "model.layers.10.self_attn.o_proj": {
1452
+ "group_size": 32,
1453
+ "bits": 4
1454
+ },
1455
+ "model.layers.10.mlp.gate_proj": {
1456
+ "group_size": 32,
1457
+ "bits": 4
1458
+ },
1459
+ "model.layers.10.mlp.down_proj": {
1460
+ "group_size": 32,
1461
+ "bits": 6
1462
+ },
1463
+ "model.layers.10.mlp.up_proj": {
1464
+ "group_size": 32,
1465
+ "bits": 4
1466
+ },
1467
+ "model.layers.11.self_attn.q_proj": {
1468
+ "group_size": 32,
1469
+ "bits": 4
1470
+ },
1471
+ "model.layers.11.self_attn.k_proj": {
1472
+ "group_size": 32,
1473
+ "bits": 4
1474
+ },
1475
+ "model.layers.11.self_attn.v_proj": {
1476
+ "group_size": 32,
1477
+ "bits": 4
1478
+ },
1479
+ "model.layers.11.self_attn.o_proj": {
1480
+ "group_size": 32,
1481
+ "bits": 4
1482
+ },
1483
+ "model.layers.11.mlp.gate_proj": {
1484
+ "group_size": 32,
1485
+ "bits": 4
1486
+ },
1487
+ "model.layers.11.mlp.down_proj": {
1488
+ "group_size": 32,
1489
+ "bits": 4
1490
+ },
1491
+ "model.layers.11.mlp.up_proj": {
1492
+ "group_size": 32,
1493
+ "bits": 4
1494
+ },
1495
+ "model.layers.12.self_attn.q_proj": {
1496
+ "group_size": 32,
1497
+ "bits": 4
1498
+ },
1499
+ "model.layers.12.self_attn.k_proj": {
1500
+ "group_size": 32,
1501
+ "bits": 4
1502
+ },
1503
+ "model.layers.12.self_attn.v_proj": {
1504
+ "group_size": 32,
1505
+ "bits": 4
1506
+ },
1507
+ "model.layers.12.self_attn.o_proj": {
1508
+ "group_size": 32,
1509
+ "bits": 4
1510
+ },
1511
+ "model.layers.12.mlp.gate_proj": {
1512
+ "group_size": 32,
1513
+ "bits": 4
1514
+ },
1515
+ "model.layers.12.mlp.down_proj": {
1516
+ "group_size": 32,
1517
+ "bits": 4
1518
+ },
1519
+ "model.layers.12.mlp.up_proj": {
1520
+ "group_size": 32,
1521
+ "bits": 4
1522
+ },
1523
+ "model.layers.13.self_attn.q_proj": {
1524
+ "group_size": 32,
1525
+ "bits": 4
1526
+ },
1527
+ "model.layers.13.self_attn.k_proj": {
1528
+ "group_size": 32,
1529
+ "bits": 4
1530
+ },
1531
+ "model.layers.13.self_attn.v_proj": {
1532
+ "group_size": 32,
1533
+ "bits": 6
1534
+ },
1535
+ "model.layers.13.self_attn.o_proj": {
1536
+ "group_size": 32,
1537
+ "bits": 4
1538
+ },
1539
+ "model.layers.13.mlp.gate_proj": {
1540
+ "group_size": 32,
1541
+ "bits": 4
1542
+ },
1543
+ "model.layers.13.mlp.down_proj": {
1544
+ "group_size": 32,
1545
+ "bits": 6
1546
+ },
1547
+ "model.layers.13.mlp.up_proj": {
1548
+ "group_size": 32,
1549
+ "bits": 4
1550
+ },
1551
+ "model.layers.14.self_attn.q_proj": {
1552
+ "group_size": 32,
1553
+ "bits": 4
1554
+ },
1555
+ "model.layers.14.self_attn.k_proj": {
1556
+ "group_size": 32,
1557
+ "bits": 4
1558
+ },
1559
+ "model.layers.14.self_attn.v_proj": {
1560
+ "group_size": 32,
1561
+ "bits": 4
1562
+ },
1563
+ "model.layers.14.self_attn.o_proj": {
1564
+ "group_size": 32,
1565
+ "bits": 4
1566
+ },
1567
+ "model.layers.14.mlp.gate_proj": {
1568
+ "group_size": 32,
1569
+ "bits": 4
1570
+ },
1571
+ "model.layers.14.mlp.down_proj": {
1572
+ "group_size": 32,
1573
+ "bits": 4
1574
+ },
1575
+ "model.layers.14.mlp.up_proj": {
1576
+ "group_size": 32,
1577
+ "bits": 4
1578
+ },
1579
+ "model.layers.15.self_attn.q_proj": {
1580
+ "group_size": 32,
1581
+ "bits": 4
1582
+ },
1583
+ "model.layers.15.self_attn.k_proj": {
1584
+ "group_size": 32,
1585
+ "bits": 4
1586
+ },
1587
+ "model.layers.15.self_attn.v_proj": {
1588
+ "group_size": 32,
1589
+ "bits": 4
1590
+ },
1591
+ "model.layers.15.self_attn.o_proj": {
1592
+ "group_size": 32,
1593
+ "bits": 4
1594
+ },
1595
+ "model.layers.15.mlp.gate_proj": {
1596
+ "group_size": 32,
1597
+ "bits": 4
1598
+ },
1599
+ "model.layers.15.mlp.down_proj": {
1600
+ "group_size": 32,
1601
+ "bits": 4
1602
+ },
1603
+ "model.layers.15.mlp.up_proj": {
1604
+ "group_size": 32,
1605
+ "bits": 4
1606
+ },
1607
+ "model.layers.16.self_attn.q_proj": {
1608
+ "group_size": 32,
1609
+ "bits": 4
1610
+ },
1611
+ "model.layers.16.self_attn.k_proj": {
1612
+ "group_size": 32,
1613
+ "bits": 4
1614
+ },
1615
+ "model.layers.16.self_attn.v_proj": {
1616
+ "group_size": 32,
1617
+ "bits": 6
1618
+ },
1619
+ "model.layers.16.self_attn.o_proj": {
1620
+ "group_size": 32,
1621
+ "bits": 4
1622
+ },
1623
+ "model.layers.16.mlp.gate_proj": {
1624
+ "group_size": 32,
1625
+ "bits": 4
1626
+ },
1627
+ "model.layers.16.mlp.down_proj": {
1628
+ "group_size": 32,
1629
+ "bits": 6
1630
+ },
1631
+ "model.layers.16.mlp.up_proj": {
1632
+ "group_size": 32,
1633
+ "bits": 4
1634
+ },
1635
+ "model.layers.17.self_attn.q_proj": {
1636
+ "group_size": 32,
1637
+ "bits": 4
1638
+ },
1639
+ "model.layers.17.self_attn.k_proj": {
1640
+ "group_size": 32,
1641
+ "bits": 4
1642
+ },
1643
+ "model.layers.17.self_attn.v_proj": {
1644
+ "group_size": 32,
1645
+ "bits": 4
1646
+ },
1647
+ "model.layers.17.self_attn.o_proj": {
1648
+ "group_size": 32,
1649
+ "bits": 4
1650
+ },
1651
+ "model.layers.17.mlp.gate_proj": {
1652
+ "group_size": 32,
1653
+ "bits": 4
1654
+ },
1655
+ "model.layers.17.mlp.down_proj": {
1656
+ "group_size": 32,
1657
+ "bits": 4
1658
+ },
1659
+ "model.layers.17.mlp.up_proj": {
1660
+ "group_size": 32,
1661
+ "bits": 4
1662
+ },
1663
+ "model.layers.18.self_attn.q_proj": {
1664
+ "group_size": 32,
1665
+ "bits": 4
1666
+ },
1667
+ "model.layers.18.self_attn.k_proj": {
1668
+ "group_size": 32,
1669
+ "bits": 4
1670
+ },
1671
+ "model.layers.18.self_attn.v_proj": {
1672
+ "group_size": 32,
1673
+ "bits": 4
1674
+ },
1675
+ "model.layers.18.self_attn.o_proj": {
1676
+ "group_size": 32,
1677
+ "bits": 4
1678
+ },
1679
+ "model.layers.18.mlp.gate_proj": {
1680
+ "group_size": 32,
1681
+ "bits": 4
1682
+ },
1683
+ "model.layers.18.mlp.down_proj": {
1684
+ "group_size": 32,
1685
+ "bits": 4
1686
+ },
1687
+ "model.layers.18.mlp.up_proj": {
1688
+ "group_size": 32,
1689
+ "bits": 4
1690
+ },
1691
+ "model.layers.19.self_attn.q_proj": {
1692
+ "group_size": 32,
1693
+ "bits": 4
1694
+ },
1695
+ "model.layers.19.self_attn.k_proj": {
1696
+ "group_size": 32,
1697
+ "bits": 4
1698
+ },
1699
+ "model.layers.19.self_attn.v_proj": {
1700
+ "group_size": 32,
1701
+ "bits": 6
1702
+ },
1703
+ "model.layers.19.self_attn.o_proj": {
1704
+ "group_size": 32,
1705
+ "bits": 4
1706
+ },
1707
+ "model.layers.19.mlp.gate_proj": {
1708
+ "group_size": 32,
1709
+ "bits": 4
1710
+ },
1711
+ "model.layers.19.mlp.down_proj": {
1712
+ "group_size": 32,
1713
+ "bits": 6
1714
+ },
1715
+ "model.layers.19.mlp.up_proj": {
1716
+ "group_size": 32,
1717
+ "bits": 4
1718
+ },
1719
+ "model.layers.20.self_attn.q_proj": {
1720
+ "group_size": 32,
1721
+ "bits": 4
1722
+ },
1723
+ "model.layers.20.self_attn.k_proj": {
1724
+ "group_size": 32,
1725
+ "bits": 4
1726
+ },
1727
+ "model.layers.20.self_attn.v_proj": {
1728
+ "group_size": 32,
1729
+ "bits": 4
1730
+ },
1731
+ "model.layers.20.self_attn.o_proj": {
1732
+ "group_size": 32,
1733
+ "bits": 4
1734
+ },
1735
+ "model.layers.20.mlp.gate_proj": {
1736
+ "group_size": 32,
1737
+ "bits": 4
1738
+ },
1739
+ "model.layers.20.mlp.down_proj": {
1740
+ "group_size": 32,
1741
+ "bits": 4
1742
+ },
1743
+ "model.layers.20.mlp.up_proj": {
1744
+ "group_size": 32,
1745
+ "bits": 4
1746
+ },
1747
+ "model.layers.21.self_attn.q_proj": {
1748
+ "group_size": 32,
1749
+ "bits": 4
1750
+ },
1751
+ "model.layers.21.self_attn.k_proj": {
1752
+ "group_size": 32,
1753
+ "bits": 4
1754
+ },
1755
+ "model.layers.21.self_attn.v_proj": {
1756
+ "group_size": 32,
1757
+ "bits": 4
1758
+ },
1759
+ "model.layers.21.self_attn.o_proj": {
1760
+ "group_size": 32,
1761
+ "bits": 4
1762
+ },
1763
+ "model.layers.21.mlp.gate_proj": {
1764
+ "group_size": 32,
1765
+ "bits": 4
1766
+ },
1767
+ "model.layers.21.mlp.down_proj": {
1768
+ "group_size": 32,
1769
+ "bits": 4
1770
+ },
1771
+ "model.layers.21.mlp.up_proj": {
1772
+ "group_size": 32,
1773
+ "bits": 4
1774
+ },
1775
+ "model.layers.22.self_attn.q_proj": {
1776
+ "group_size": 32,
1777
+ "bits": 4
1778
+ },
1779
+ "model.layers.22.self_attn.k_proj": {
1780
+ "group_size": 32,
1781
+ "bits": 4
1782
+ },
1783
+ "model.layers.22.self_attn.v_proj": {
1784
+ "group_size": 32,
1785
+ "bits": 6
1786
+ },
1787
+ "model.layers.22.self_attn.o_proj": {
1788
+ "group_size": 32,
1789
+ "bits": 4
1790
+ },
1791
+ "model.layers.22.mlp.gate_proj": {
1792
+ "group_size": 32,
1793
+ "bits": 4
1794
+ },
1795
+ "model.layers.22.mlp.down_proj": {
1796
+ "group_size": 32,
1797
+ "bits": 6
1798
+ },
1799
+ "model.layers.22.mlp.up_proj": {
1800
+ "group_size": 32,
1801
+ "bits": 4
1802
+ },
1803
+ "model.layers.23.self_attn.q_proj": {
1804
+ "group_size": 32,
1805
+ "bits": 4
1806
+ },
1807
+ "model.layers.23.self_attn.k_proj": {
1808
+ "group_size": 32,
1809
+ "bits": 4
1810
+ },
1811
+ "model.layers.23.self_attn.v_proj": {
1812
+ "group_size": 32,
1813
+ "bits": 4
1814
+ },
1815
+ "model.layers.23.self_attn.o_proj": {
1816
+ "group_size": 32,
1817
+ "bits": 4
1818
+ },
1819
+ "model.layers.23.mlp.gate_proj": {
1820
+ "group_size": 32,
1821
+ "bits": 4
1822
+ },
1823
+ "model.layers.23.mlp.down_proj": {
1824
+ "group_size": 32,
1825
+ "bits": 4
1826
+ },
1827
+ "model.layers.23.mlp.up_proj": {
1828
+ "group_size": 32,
1829
+ "bits": 4
1830
+ },
1831
+ "model.layers.24.self_attn.q_proj": {
1832
+ "group_size": 32,
1833
+ "bits": 4
1834
+ },
1835
+ "model.layers.24.self_attn.k_proj": {
1836
+ "group_size": 32,
1837
+ "bits": 4
1838
+ },
1839
+ "model.layers.24.self_attn.v_proj": {
1840
+ "group_size": 32,
1841
+ "bits": 4
1842
+ },
1843
+ "model.layers.24.self_attn.o_proj": {
1844
+ "group_size": 32,
1845
+ "bits": 4
1846
+ },
1847
+ "model.layers.24.mlp.gate_proj": {
1848
+ "group_size": 32,
1849
+ "bits": 4
1850
+ },
1851
+ "model.layers.24.mlp.down_proj": {
1852
+ "group_size": 32,
1853
+ "bits": 4
1854
+ },
1855
+ "model.layers.24.mlp.up_proj": {
1856
+ "group_size": 32,
1857
+ "bits": 4
1858
+ },
1859
+ "model.layers.25.self_attn.q_proj": {
1860
+ "group_size": 32,
1861
+ "bits": 4
1862
+ },
1863
+ "model.layers.25.self_attn.k_proj": {
1864
+ "group_size": 32,
1865
+ "bits": 4
1866
+ },
1867
+ "model.layers.25.self_attn.v_proj": {
1868
+ "group_size": 32,
1869
+ "bits": 6
1870
+ },
1871
+ "model.layers.25.self_attn.o_proj": {
1872
+ "group_size": 32,
1873
+ "bits": 4
1874
+ },
1875
+ "model.layers.25.mlp.gate_proj": {
1876
+ "group_size": 32,
1877
+ "bits": 4
1878
+ },
1879
+ "model.layers.25.mlp.down_proj": {
1880
+ "group_size": 32,
1881
+ "bits": 6
1882
+ },
1883
+ "model.layers.25.mlp.up_proj": {
1884
+ "group_size": 32,
1885
+ "bits": 4
1886
+ },
1887
+ "model.layers.26.self_attn.q_proj": {
1888
+ "group_size": 32,
1889
+ "bits": 4
1890
+ },
1891
+ "model.layers.26.self_attn.k_proj": {
1892
+ "group_size": 32,
1893
+ "bits": 4
1894
+ },
1895
+ "model.layers.26.self_attn.v_proj": {
1896
+ "group_size": 32,
1897
+ "bits": 4
1898
+ },
1899
+ "model.layers.26.self_attn.o_proj": {
1900
+ "group_size": 32,
1901
+ "bits": 4
1902
+ },
1903
+ "model.layers.26.mlp.gate_proj": {
1904
+ "group_size": 32,
1905
+ "bits": 4
1906
+ },
1907
+ "model.layers.26.mlp.down_proj": {
1908
+ "group_size": 32,
1909
+ "bits": 4
1910
+ },
1911
+ "model.layers.26.mlp.up_proj": {
1912
+ "group_size": 32,
1913
+ "bits": 4
1914
+ },
1915
+ "model.layers.27.self_attn.q_proj": {
1916
+ "group_size": 32,
1917
+ "bits": 4
1918
+ },
1919
+ "model.layers.27.self_attn.k_proj": {
1920
+ "group_size": 32,
1921
+ "bits": 4
1922
+ },
1923
+ "model.layers.27.self_attn.v_proj": {
1924
+ "group_size": 32,
1925
+ "bits": 4
1926
+ },
1927
+ "model.layers.27.self_attn.o_proj": {
1928
+ "group_size": 32,
1929
+ "bits": 4
1930
+ },
1931
+ "model.layers.27.mlp.gate_proj": {
1932
+ "group_size": 32,
1933
+ "bits": 4
1934
+ },
1935
+ "model.layers.27.mlp.down_proj": {
1936
+ "group_size": 32,
1937
+ "bits": 4
1938
+ },
1939
+ "model.layers.27.mlp.up_proj": {
1940
+ "group_size": 32,
1941
+ "bits": 4
1942
+ },
1943
+ "model.layers.28.self_attn.q_proj": {
1944
+ "group_size": 32,
1945
+ "bits": 4
1946
+ },
1947
+ "model.layers.28.self_attn.k_proj": {
1948
+ "group_size": 32,
1949
+ "bits": 4
1950
+ },
1951
+ "model.layers.28.self_attn.v_proj": {
1952
+ "group_size": 32,
1953
+ "bits": 6
1954
+ },
1955
+ "model.layers.28.self_attn.o_proj": {
1956
+ "group_size": 32,
1957
+ "bits": 4
1958
+ },
1959
+ "model.layers.28.mlp.gate_proj": {
1960
+ "group_size": 32,
1961
+ "bits": 4
1962
+ },
1963
+ "model.layers.28.mlp.down_proj": {
1964
+ "group_size": 32,
1965
+ "bits": 6
1966
+ },
1967
+ "model.layers.28.mlp.up_proj": {
1968
+ "group_size": 32,
1969
+ "bits": 4
1970
+ },
1971
+ "model.layers.29.self_attn.q_proj": {
1972
+ "group_size": 32,
1973
+ "bits": 4
1974
+ },
1975
+ "model.layers.29.self_attn.k_proj": {
1976
+ "group_size": 32,
1977
+ "bits": 4
1978
+ },
1979
+ "model.layers.29.self_attn.v_proj": {
1980
+ "group_size": 32,
1981
+ "bits": 4
1982
+ },
1983
+ "model.layers.29.self_attn.o_proj": {
1984
+ "group_size": 32,
1985
+ "bits": 4
1986
+ },
1987
+ "model.layers.29.mlp.gate_proj": {
1988
+ "group_size": 32,
1989
+ "bits": 4
1990
+ },
1991
+ "model.layers.29.mlp.down_proj": {
1992
+ "group_size": 32,
1993
+ "bits": 4
1994
+ },
1995
+ "model.layers.29.mlp.up_proj": {
1996
+ "group_size": 32,
1997
+ "bits": 4
1998
+ },
1999
+ "model.layers.30.self_attn.q_proj": {
2000
+ "group_size": 32,
2001
+ "bits": 4
2002
+ },
2003
+ "model.layers.30.self_attn.k_proj": {
2004
+ "group_size": 32,
2005
+ "bits": 4
2006
+ },
2007
+ "model.layers.30.self_attn.v_proj": {
2008
+ "group_size": 32,
2009
+ "bits": 4
2010
+ },
2011
+ "model.layers.30.self_attn.o_proj": {
2012
+ "group_size": 32,
2013
+ "bits": 4
2014
+ },
2015
+ "model.layers.30.mlp.gate_proj": {
2016
+ "group_size": 32,
2017
+ "bits": 4
2018
+ },
2019
+ "model.layers.30.mlp.down_proj": {
2020
+ "group_size": 32,
2021
+ "bits": 4
2022
+ },
2023
+ "model.layers.30.mlp.up_proj": {
2024
+ "group_size": 32,
2025
+ "bits": 4
2026
+ },
2027
+ "model.layers.31.self_attn.q_proj": {
2028
+ "group_size": 32,
2029
+ "bits": 4
2030
+ },
2031
+ "model.layers.31.self_attn.k_proj": {
2032
+ "group_size": 32,
2033
+ "bits": 4
2034
+ },
2035
+ "model.layers.31.self_attn.v_proj": {
2036
+ "group_size": 32,
2037
+ "bits": 6
2038
+ },
2039
+ "model.layers.31.self_attn.o_proj": {
2040
+ "group_size": 32,
2041
+ "bits": 4
2042
+ },
2043
+ "model.layers.31.mlp.gate_proj": {
2044
+ "group_size": 32,
2045
+ "bits": 4
2046
+ },
2047
+ "model.layers.31.mlp.down_proj": {
2048
+ "group_size": 32,
2049
+ "bits": 6
2050
+ },
2051
+ "model.layers.31.mlp.up_proj": {
2052
+ "group_size": 32,
2053
+ "bits": 4
2054
+ },
2055
+ "model.layers.32.self_attn.q_proj": {
2056
+ "group_size": 32,
2057
+ "bits": 4
2058
+ },
2059
+ "model.layers.32.self_attn.k_proj": {
2060
+ "group_size": 32,
2061
+ "bits": 4
2062
+ },
2063
+ "model.layers.32.self_attn.v_proj": {
2064
+ "group_size": 32,
2065
+ "bits": 4
2066
+ },
2067
+ "model.layers.32.self_attn.o_proj": {
2068
+ "group_size": 32,
2069
+ "bits": 4
2070
+ },
2071
+ "model.layers.32.mlp.gate_proj": {
2072
+ "group_size": 32,
2073
+ "bits": 4
2074
+ },
2075
+ "model.layers.32.mlp.down_proj": {
2076
+ "group_size": 32,
2077
+ "bits": 4
2078
+ },
2079
+ "model.layers.32.mlp.up_proj": {
2080
+ "group_size": 32,
2081
+ "bits": 4
2082
+ },
2083
+ "model.layers.33.self_attn.q_proj": {
2084
+ "group_size": 32,
2085
+ "bits": 4
2086
+ },
2087
+ "model.layers.33.self_attn.k_proj": {
2088
+ "group_size": 32,
2089
+ "bits": 4
2090
+ },
2091
+ "model.layers.33.self_attn.v_proj": {
2092
+ "group_size": 32,
2093
+ "bits": 4
2094
+ },
2095
+ "model.layers.33.self_attn.o_proj": {
2096
+ "group_size": 32,
2097
+ "bits": 4
2098
+ },
2099
+ "model.layers.33.mlp.gate_proj": {
2100
+ "group_size": 32,
2101
+ "bits": 4
2102
+ },
2103
+ "model.layers.33.mlp.down_proj": {
2104
+ "group_size": 32,
2105
+ "bits": 4
2106
+ },
2107
+ "model.layers.33.mlp.up_proj": {
2108
+ "group_size": 32,
2109
+ "bits": 4
2110
+ },
2111
+ "model.layers.34.self_attn.q_proj": {
2112
+ "group_size": 32,
2113
+ "bits": 4
2114
+ },
2115
+ "model.layers.34.self_attn.k_proj": {
2116
+ "group_size": 32,
2117
+ "bits": 4
2118
+ },
2119
+ "model.layers.34.self_attn.v_proj": {
2120
+ "group_size": 32,
2121
+ "bits": 6
2122
+ },
2123
+ "model.layers.34.self_attn.o_proj": {
2124
+ "group_size": 32,
2125
+ "bits": 4
2126
+ },
2127
+ "model.layers.34.mlp.gate_proj": {
2128
+ "group_size": 32,
2129
+ "bits": 4
2130
+ },
2131
+ "model.layers.34.mlp.down_proj": {
2132
+ "group_size": 32,
2133
+ "bits": 6
2134
+ },
2135
+ "model.layers.34.mlp.up_proj": {
2136
+ "group_size": 32,
2137
+ "bits": 4
2138
+ },
2139
+ "model.layers.35.self_attn.q_proj": {
2140
+ "group_size": 32,
2141
+ "bits": 4
2142
+ },
2143
+ "model.layers.35.self_attn.k_proj": {
2144
+ "group_size": 32,
2145
+ "bits": 4
2146
+ },
2147
+ "model.layers.35.self_attn.v_proj": {
2148
+ "group_size": 32,
2149
+ "bits": 6
2150
+ },
2151
+ "model.layers.35.self_attn.o_proj": {
2152
+ "group_size": 32,
2153
+ "bits": 4
2154
+ },
2155
+ "model.layers.35.mlp.gate_proj": {
2156
+ "group_size": 32,
2157
+ "bits": 4
2158
+ },
2159
+ "model.layers.35.mlp.down_proj": {
2160
+ "group_size": 32,
2161
+ "bits": 6
2162
+ },
2163
+ "model.layers.35.mlp.up_proj": {
2164
+ "group_size": 32,
2165
+ "bits": 4
2166
+ },
2167
+ "model.layers.36.self_attn.q_proj": {
2168
+ "group_size": 32,
2169
+ "bits": 4
2170
+ },
2171
+ "model.layers.36.self_attn.k_proj": {
2172
+ "group_size": 32,
2173
+ "bits": 4
2174
+ },
2175
+ "model.layers.36.self_attn.v_proj": {
2176
+ "group_size": 32,
2177
+ "bits": 6
2178
+ },
2179
+ "model.layers.36.self_attn.o_proj": {
2180
+ "group_size": 32,
2181
+ "bits": 4
2182
+ },
2183
+ "model.layers.36.mlp.gate_proj": {
2184
+ "group_size": 32,
2185
+ "bits": 4
2186
+ },
2187
+ "model.layers.36.mlp.down_proj": {
2188
+ "group_size": 32,
2189
+ "bits": 6
2190
+ },
2191
+ "model.layers.36.mlp.up_proj": {
2192
+ "group_size": 32,
2193
+ "bits": 4
2194
+ },
2195
+ "model.layers.37.self_attn.q_proj": {
2196
+ "group_size": 32,
2197
+ "bits": 4
2198
+ },
2199
+ "model.layers.37.self_attn.k_proj": {
2200
+ "group_size": 32,
2201
+ "bits": 4
2202
+ },
2203
+ "model.layers.37.self_attn.v_proj": {
2204
+ "group_size": 32,
2205
+ "bits": 6
2206
+ },
2207
+ "model.layers.37.self_attn.o_proj": {
2208
+ "group_size": 32,
2209
+ "bits": 4
2210
+ },
2211
+ "model.layers.37.mlp.gate_proj": {
2212
+ "group_size": 32,
2213
+ "bits": 4
2214
+ },
2215
+ "model.layers.37.mlp.down_proj": {
2216
+ "group_size": 32,
2217
+ "bits": 6
2218
+ },
2219
+ "model.layers.37.mlp.up_proj": {
2220
+ "group_size": 32,
2221
+ "bits": 4
2222
+ },
2223
+ "model.layers.38.self_attn.q_proj": {
2224
+ "group_size": 32,
2225
+ "bits": 4
2226
+ },
2227
+ "model.layers.38.self_attn.k_proj": {
2228
+ "group_size": 32,
2229
+ "bits": 4
2230
+ },
2231
+ "model.layers.38.self_attn.v_proj": {
2232
+ "group_size": 32,
2233
+ "bits": 6
2234
+ },
2235
+ "model.layers.38.self_attn.o_proj": {
2236
+ "group_size": 32,
2237
+ "bits": 4
2238
+ },
2239
+ "model.layers.38.mlp.gate_proj": {
2240
+ "group_size": 32,
2241
+ "bits": 4
2242
+ },
2243
+ "model.layers.38.mlp.down_proj": {
2244
+ "group_size": 32,
2245
+ "bits": 6
2246
+ },
2247
+ "model.layers.38.mlp.up_proj": {
2248
+ "group_size": 32,
2249
+ "bits": 4
2250
+ },
2251
+ "model.layers.39.self_attn.q_proj": {
2252
+ "group_size": 32,
2253
+ "bits": 4
2254
+ },
2255
+ "model.layers.39.self_attn.k_proj": {
2256
+ "group_size": 32,
2257
+ "bits": 4
2258
+ },
2259
+ "model.layers.39.self_attn.v_proj": {
2260
+ "group_size": 32,
2261
+ "bits": 6
2262
+ },
2263
+ "model.layers.39.self_attn.o_proj": {
2264
+ "group_size": 32,
2265
+ "bits": 4
2266
+ },
2267
+ "model.layers.39.mlp.gate_proj": {
2268
+ "group_size": 32,
2269
+ "bits": 4
2270
+ },
2271
+ "model.layers.39.mlp.down_proj": {
2272
+ "group_size": 32,
2273
+ "bits": 6
2274
+ },
2275
+ "model.layers.39.mlp.up_proj": {
2276
+ "group_size": 32,
2277
+ "bits": 4
2278
+ },
2279
+ "lm_head": {
2280
+ "group_size": 32,
2281
+ "bits": 6
2282
+ }
2283
+ },
2284
+ "rms_norm_eps": 1e-05,
2285
+ "rope_theta": 1000000.0,
2286
+ "sliding_window": null,
2287
+ "tie_word_embeddings": false,
2288
+ "torch_dtype": "bfloat16",
2289
+ "transformers_version": "4.43.0.dev0",
2290
+ "use_cache": true,
2291
+ "vocab_size": 131072
2292
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.0.dev0"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dd7dc0d6388397da864aed5bcc78e6b5a9df46bd915e86e5e04a5163f1416a
3
+ size 5335256679
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5f3c28c7d2f1765d50aa269e5705f493b472ada17c99a4e87c2d126032a1b6
3
+ size 2881272143
model.safetensors.index.json ADDED
@@ -0,0 +1,935 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8216422400,
4
+ "total_parameters": 12247782400
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model-00002-of-00002.safetensors",
8
+ "lm_head.scales": "model-00002-of-00002.safetensors",
9
+ "lm_head.weight": "model-00002-of-00002.safetensors",
10
+ "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
11
+ "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
12
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
61
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
64
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
65
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
67
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
68
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
71
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
84
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
85
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
87
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
90
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
94
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
95
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
97
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
98
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
100
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
101
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
103
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
107
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
108
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
110
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
111
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
113
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
114
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
117
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
118
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
120
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
121
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
123
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
124
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
126
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
127
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
130
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
131
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
133
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
136
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
137
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
140
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
141
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
143
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
144
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
146
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
147
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
149
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
150
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
153
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
154
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
156
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
157
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
159
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
163
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
164
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
166
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
167
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
169
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
170
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
172
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
173
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
176
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
179
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
180
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
182
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
183
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
186
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
187
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
189
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
190
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
192
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
193
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
195
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
196
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
199
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
200
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
202
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
205
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
206
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
209
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
210
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
212
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
213
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
215
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
216
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
218
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
219
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
222
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
223
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
225
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
226
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
228
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
232
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
233
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
235
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
236
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
238
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
239
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
241
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
242
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
245
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
248
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
249
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
251
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
252
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
255
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
256
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
258
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
259
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
261
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
262
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
264
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
265
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
268
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
269
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
271
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
274
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
275
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
278
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
279
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
281
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
282
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
284
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
285
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
287
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
288
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
291
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
292
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
294
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
295
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
297
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
301
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
302
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
304
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
305
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
307
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
308
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
310
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
311
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
314
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
317
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
318
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
320
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
321
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
324
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
325
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
327
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
328
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
330
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
331
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
333
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
334
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
337
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
338
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
340
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
341
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
343
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
344
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
347
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
348
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
350
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
351
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
353
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
354
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
356
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
357
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
360
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
361
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
363
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
364
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
366
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
367
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
370
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
371
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
373
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
374
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
376
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
377
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
379
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
380
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
383
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
384
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
386
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
387
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
389
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
390
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
393
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
394
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
396
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
397
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
399
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
400
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
402
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
403
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
406
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
407
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
409
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
410
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
412
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
416
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
417
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
419
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
420
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
422
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
423
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
425
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
426
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
429
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
432
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
433
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
435
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
436
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
439
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
440
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
442
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
443
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
445
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
446
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
448
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
449
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
452
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
453
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
455
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
458
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
459
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
462
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
463
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
465
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
466
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
468
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
471
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
472
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
474
+ "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
475
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
476
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
477
+ "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
478
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
479
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
481
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
482
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
483
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
484
+ "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
485
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
486
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
488
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
489
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
490
+ "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
491
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
492
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
493
+ "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
494
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
495
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
496
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
497
+ "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
498
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
499
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
500
+ "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
501
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
502
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
503
+ "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
504
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
505
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
506
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
507
+ "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
508
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
509
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
510
+ "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
511
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
512
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
513
+ "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
514
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
515
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
516
+ "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
517
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
518
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
519
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
520
+ "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
521
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
522
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
523
+ "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
524
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
525
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
526
+ "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
527
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
528
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
529
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
530
+ "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
531
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
532
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
533
+ "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
534
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
535
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
536
+ "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
537
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
538
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
539
+ "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
540
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
541
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
542
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
543
+ "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
544
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
545
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
546
+ "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
547
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
548
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
549
+ "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
550
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
551
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
552
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
553
+ "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
554
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
555
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
556
+ "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
557
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
558
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
559
+ "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
560
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
561
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
562
+ "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
563
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
564
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
565
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
566
+ "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
567
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
568
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
569
+ "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
570
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
571
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
572
+ "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
573
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
574
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
575
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
576
+ "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
577
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
578
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
579
+ "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
580
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
581
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
582
+ "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
583
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
584
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
585
+ "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
586
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
587
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
588
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
589
+ "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
590
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
591
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
592
+ "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
593
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
594
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
595
+ "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
596
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
597
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
598
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
599
+ "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
600
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
601
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
602
+ "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
603
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
604
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
605
+ "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
606
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
607
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
608
+ "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
609
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
610
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
611
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
612
+ "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
613
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
614
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
615
+ "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
616
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
617
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
618
+ "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
619
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
620
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
621
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
622
+ "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
623
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
624
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
625
+ "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
626
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
627
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
628
+ "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
629
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
630
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
631
+ "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
632
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
633
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
634
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
635
+ "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
636
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
637
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
638
+ "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
639
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
640
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
641
+ "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
642
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
643
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
644
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
645
+ "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
646
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
647
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
648
+ "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
649
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
650
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
651
+ "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
652
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
653
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
654
+ "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
655
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
656
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
657
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
658
+ "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
659
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
660
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
661
+ "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
662
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
663
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
664
+ "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
665
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
666
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
667
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
668
+ "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
669
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
670
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
671
+ "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
672
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
673
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
674
+ "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
675
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
676
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
677
+ "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
678
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
679
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
680
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
681
+ "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
682
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
683
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
684
+ "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
685
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
686
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
687
+ "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
688
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
689
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
690
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
691
+ "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
692
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
693
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
694
+ "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
695
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
696
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
697
+ "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
698
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
699
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
700
+ "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
701
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
702
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
703
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
704
+ "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
705
+ "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
706
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
707
+ "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
708
+ "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
709
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
710
+ "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
711
+ "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
712
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
713
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
714
+ "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
715
+ "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
716
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
717
+ "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
718
+ "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
719
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
721
+ "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
722
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
723
+ "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
724
+ "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
725
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
726
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
727
+ "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
728
+ "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
729
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
730
+ "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
731
+ "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
732
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
733
+ "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
734
+ "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
735
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
736
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
737
+ "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
738
+ "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
739
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
740
+ "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
741
+ "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
742
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
743
+ "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
744
+ "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
745
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
746
+ "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
747
+ "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
748
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
749
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
750
+ "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
751
+ "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
752
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
753
+ "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
754
+ "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
755
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
756
+ "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
757
+ "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
758
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
759
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
760
+ "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
761
+ "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
762
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
763
+ "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
764
+ "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
765
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
766
+ "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
767
+ "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
768
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
769
+ "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
770
+ "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
771
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
772
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
773
+ "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
774
+ "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
775
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
776
+ "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
777
+ "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
778
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
779
+ "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
780
+ "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
781
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
782
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
783
+ "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
784
+ "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
785
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
786
+ "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
787
+ "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
788
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
789
+ "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
790
+ "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
791
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
792
+ "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
793
+ "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
794
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
795
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
796
+ "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
797
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
798
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
799
+ "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
800
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
801
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
802
+ "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
803
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
804
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
805
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
806
+ "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
807
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
808
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
809
+ "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
810
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
811
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
812
+ "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
813
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
814
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
815
+ "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
816
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
817
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
818
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
819
+ "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
820
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
821
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
822
+ "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
823
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
824
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
825
+ "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
826
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
827
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
828
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
829
+ "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
830
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
831
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
832
+ "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
833
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
834
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
835
+ "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
836
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
837
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
838
+ "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
839
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
840
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
841
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
842
+ "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
843
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
844
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
845
+ "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
846
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
847
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
848
+ "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
849
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
850
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
851
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
852
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
853
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
854
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
855
+ "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
856
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
857
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
858
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
859
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
860
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
861
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
862
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
863
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
864
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
865
+ "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
866
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
867
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
868
+ "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
869
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
870
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
871
+ "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
872
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
873
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
874
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
875
+ "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
876
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
877
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
878
+ "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
879
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
880
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
881
+ "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
882
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
883
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
884
+ "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
885
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
886
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
887
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
888
+ "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
889
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
890
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
891
+ "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
892
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
893
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
894
+ "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
895
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
896
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
897
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
898
+ "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
899
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
900
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
901
+ "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
902
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
903
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
904
+ "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
905
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
906
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
907
+ "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
908
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
909
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
910
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
911
+ "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
912
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
913
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
914
+ "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
915
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
916
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
917
+ "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
918
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
919
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
920
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
921
+ "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
922
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
923
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
924
+ "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
925
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
926
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
927
+ "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
928
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
929
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
930
+ "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
931
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
932
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
933
+ "model.norm.weight": "model-00002-of-00002.safetensors"
934
+ }
935
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
3
+ size 17078292
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff