Hugging Face's logo

ibm-granite
/
granite-4.1-30b-fp8

Text Generation
Transformers
Safetensors
GGUF
granite
language
granite-4.1
conversational
compressed-tensors
Model card Files
xet
 Community
yousafshah commited on
Commit
12c94c9
·
verified ·
1 Parent(s): b372c05

Granite-4.1 Model family

Browse files
Files changed (19) hide show
  1. README.md +20 -3
  2. chat_template.jinja +114 -0
  3. config.json +83 -0
  4. generation_config.json +7 -0
  5. merges.txt +0 -0
  6. model-00001-of-00007.safetensors +3 -0
  7. model-00002-of-00007.safetensors +3 -0
  8. model-00003-of-00007.safetensors +3 -0
  9. model-00004-of-00007.safetensors +3 -0
  10. model-00005-of-00007.safetensors +3 -0
  11. model-00006-of-00007.safetensors +3 -0
  12. model-00007-of-00007.safetensors +3 -0
  13. model.safetensors.index.json +1035 -0
  14. model.sig +1 -0
  15. recipe.yaml +7 -0
  16. special_tokens_map.json +30 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +783 -0
  19. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,20 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - language
6
+ - granite-4.1
7
+ - gguf
8
+ base_model:
9
+ - ibm-granite/granite-4.1-30b
10
+ ---
11
+
12
+ ### Granite-4.1-30B (FP8)
13
+
14
+
15
+ > [!NOTE]
16
+ > This repository contains the FP8 version of **4.1-30B**.
17
+ >
18
+ > Please refer to the the original instruct model's model card for additional details:
19
+ > https://huggingface.co/ibm-granite/granite-4.1-30b
20
+
chat_template.jinja ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
+ {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
+ {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
+ {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
+ {%- if available_tools is defined and available_tools %}
6
+ {%- set tools = available_tools %}
7
+ {%- endif %}
8
+ {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
9
+ documents_system_message=documents_system_message_prefix,
10
+ system_message=''
11
+ ) %}
12
+ {%- if tools %}
13
+ {%- for tool in tools %}
14
+ {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
15
+ {%- endfor %}
16
+ {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
17
+ {%- else %}
18
+ {%- set ns.tools_system_message = '' %}
19
+ {%- endif %}
20
+ {%- if documents %}
21
+ {%- for document in documents %}
22
+ {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
23
+ {%- endfor %}
24
+ {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
25
+ {%- else %}
26
+ {%- set ns.documents_system_message = '' %}
27
+ {%- endif %}
28
+ {%- if messages[0].role == 'system' %}
29
+ {%- if messages[0].content is string %}
30
+ {%- set ns.system_message = messages[0].content %}
31
+ {%- elif messages[0].content is iterable %}
32
+ {%- for entry in messages[0].content %}
33
+ {%- if entry.type== 'text' %}
34
+ {%- if ns.system_message != '' %}
35
+ {%- set ns.system_message = ns.system_message + '\n' %}
36
+ {%- endif %}
37
+ {%- set ns.system_message = ns.system_message + entry.text %}
38
+ {%- endif %}
39
+ {%- endfor %}
40
+ {%- endif %}
41
+ {%- if tools and documents %}
42
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
43
+ {%- elif tools %}
44
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
45
+ {%- elif documents %}
46
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
47
+ {%- endif %}
48
+ {%- else %}
49
+ {%- if tools and documents %}
50
+ {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
51
+ {%- elif tools %}
52
+ {%- set ns.system_message = ns.tools_system_message %}
53
+ {%- elif documents %}
54
+ {%- set ns.system_message = ns.documents_system_message %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if ns.system_message %}
58
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
59
+ {%- endif %}
60
+ {%- for message in messages %}
61
+ {%- set content = namespace(val='') %}
62
+ {%- if message.content is string %}
63
+ {%- set content.val = message.content %}
64
+ {%- else %}
65
+ {%- if message.content is iterable %}
66
+ {%- for entry in message.content %}
67
+ {%- if entry.type== 'text' %}
68
+ {%- if content.val != '' %}
69
+ {%- set content.val = content.val + '\n' %}
70
+ {%- endif %}
71
+ {%- set content.val = content.val + entry.text %}
72
+ {%- endif %}
73
+ {%- endfor %}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
77
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
78
+ {%- elif message.role == 'assistant' %}
79
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
80
+ {%- if message.tool_calls %}
81
+ {%- for tool_call in message.tool_calls %}
82
+ {%- if (loop.first and content.val) or (not loop.first) %}
83
+ {{- '\n' }}
84
+ {%- endif %}
85
+ {%- if tool_call.function %}
86
+ {%- set tool_call = tool_call.function %}
87
+ {%- endif %}
88
+ {{- '<tool_call>\n{"name": "' }}
89
+ {{- tool_call.name }}
90
+ {{- '", "arguments": ' }}
91
+ {%- if tool_call.arguments is string %}
92
+ {{- tool_call.arguments }}
93
+ {%- else %}
94
+ {{- tool_call.arguments | tojson }}
95
+ {%- endif %}
96
+ {{- '}\n</tool_call>' }}
97
+ {%- endfor %}
98
+ {%- endif %}
99
+ {{- '<|end_of_text|>\n' }}
100
+ {%- elif message.role == 'tool' %}
101
+ {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
102
+ {{- '<|start_of_role|>user<|end_of_role|>' }}
103
+ {%- endif %}
104
+ {{- '\n<tool_response>\n' }}
105
+ {{- content.val }}
106
+ {{- '\n</tool_response>' }}
107
+ {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
108
+ {{- '<|end_of_text|>\n' }}
109
+ {%- endif %}
110
+ {%- endif %}
111
+ {%- endfor %}
112
+ {%- if add_generation_prompt %}
113
+ {{- '<|start_of_role|>assistant<|end_of_role|>' }}
114
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 100257,
9
+ "dtype": "bfloat16",
10
+ "embedding_multiplier": 12.0,
11
+ "eos_token_id": 100257,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "init_method": "mup",
15
+ "initializer_range": 0.1,
16
+ "intermediate_size": 32768,
17
+ "logits_scaling": 16.0,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "granite",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 64,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 100256,
25
+ "quantization_config": {
26
+ "config_groups": {
27
+ "group_0": {
28
+ "format": "float-quantized",
29
+ "input_activations": {
30
+ "actorder": null,
31
+ "block_structure": null,
32
+ "dynamic": true,
33
+ "group_size": null,
34
+ "num_bits": 8,
35
+ "observer": null,
36
+ "observer_kwargs": {},
37
+ "scale_dtype": null,
38
+ "strategy": "token",
39
+ "symmetric": true,
40
+ "type": "float",
41
+ "zp_dtype": null
42
+ },
43
+ "output_activations": null,
44
+ "targets": [
45
+ "Linear"
46
+ ],
47
+ "weights": {
48
+ "actorder": null,
49
+ "block_structure": null,
50
+ "dynamic": false,
51
+ "group_size": null,
52
+ "num_bits": 8,
53
+ "observer": "memoryless_minmax",
54
+ "observer_kwargs": {},
55
+ "scale_dtype": null,
56
+ "strategy": "channel",
57
+ "symmetric": true,
58
+ "type": "float",
59
+ "zp_dtype": null
60
+ }
61
+ }
62
+ },
63
+ "format": "float-quantized",
64
+ "global_compression_ratio": null,
65
+ "ignore": [
66
+ "lm_head"
67
+ ],
68
+ "kv_cache_scheme": null,
69
+ "quant_method": "compressed-tensors",
70
+ "quantization_status": "compressed",
71
+ "sparsity_config": {},
72
+ "transform_config": {},
73
+ "version": "0.14.0.1"
74
+ },
75
+ "residual_multiplier": 0.175,
76
+ "rms_norm_eps": 1e-05,
77
+ "rope_scaling": null,
78
+ "rope_theta": 50000000,
79
+ "tie_word_embeddings": true,
80
+ "transformers_version": "4.57.6",
81
+ "use_cache": false,
82
+ "vocab_size": 100352
83
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100256,
6
+ "transformers_version": "4.57.6"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02cdba0d82a6ba417ceaf1b3d0a191cfb27eaeebabb82742a2d65e525923847c
3
+ size 4867016248
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5def3b7f316ab206ce67da2eb7feb8387d2c2a570b828a12a9684dacf15ad965
3
+ size 4892516184
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bdefeb3ee59e92e47490be595f1d7adb1f0743e06495d24c0ed92f422472653
3
+ size 4892516208
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e094fb05b6b127c5d111be83e7413e7781e5717ddedfde1e660a1d293d0058
3
+ size 4892516208
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdb35a492d553cea69d16c3e7c0bc0ff66e3a1ddd9fd9692d505313573c5277
3
+ size 4892516208
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6670367b39ffe7d7d0bbcd1796a99a1a99fa25ac3cc0fbd5ef1ad82ecd6520f7
3
+ size 4850560016
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666fb265c7bf4c442eae6a7f3d40dbc92783f6e6ab955a331b613ec50358eac4
3
+ size 822083712
model.safetensors.index.json ADDED
@@ -0,0 +1,1035 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 29281882112,
4
+ "total_size": 30109605888
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
21
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
23
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
27
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
28
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
29
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
30
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
31
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
32
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
33
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
34
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
35
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
36
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
37
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
38
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
39
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
40
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
41
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
42
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
43
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
44
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
45
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
46
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
47
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
48
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
49
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
50
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
52
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
53
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
54
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
55
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
56
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
57
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
58
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
59
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
60
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
61
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
62
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
63
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
64
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
65
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
66
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
67
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
68
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
69
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
70
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
71
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
72
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
73
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
74
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
75
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
76
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
77
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
78
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
79
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
80
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
81
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
82
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
84
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
85
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
86
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
87
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
88
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
89
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
90
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
91
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
92
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
93
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
94
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
95
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
96
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
97
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
98
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
99
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
100
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
101
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
102
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
103
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
104
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
105
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
106
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
107
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
108
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
109
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
110
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
111
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
112
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
113
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
114
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
115
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
116
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
117
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
118
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
119
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
120
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
121
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
122
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
123
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
124
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
125
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
126
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
127
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
128
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
129
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
130
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
131
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
132
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
133
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
134
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
135
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
136
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
137
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
138
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
139
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
140
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
141
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
142
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
143
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
144
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
145
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
146
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
147
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
148
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
149
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
150
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
151
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
152
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
153
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
154
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
155
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
156
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
157
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
158
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
159
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
160
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
161
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
162
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
164
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
165
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
166
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
167
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
168
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
169
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors",
170
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
171
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
172
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
173
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
174
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
175
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
176
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
177
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
178
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
179
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
180
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
181
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
182
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
183
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
184
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
185
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors",
186
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
187
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
188
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
189
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
190
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
191
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
192
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
193
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
194
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
196
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
198
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
199
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
200
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
201
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
202
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
203
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
204
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
205
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
206
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
207
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
208
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
209
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
210
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
211
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
212
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
213
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
214
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
215
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
216
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
217
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
218
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
219
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
220
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
221
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
222
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
223
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
224
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
225
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
226
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00007.safetensors",
227
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
228
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00007.safetensors",
229
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
230
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00007.safetensors",
231
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
232
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00007.safetensors",
233
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
234
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
235
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
236
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
237
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
238
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
239
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
240
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
241
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
242
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
243
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
244
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
245
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
246
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
247
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
248
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
249
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
250
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
251
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
252
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
253
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
254
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
255
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
256
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
257
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
258
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
259
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
260
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
261
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
262
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
263
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
264
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
265
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
266
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
267
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
268
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
269
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
270
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
271
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
272
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
273
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
274
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
276
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
277
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
278
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
279
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
280
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
281
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
282
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
283
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
284
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
285
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
286
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
287
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
288
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
291
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
292
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
293
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
294
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
295
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
296
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
297
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
298
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
299
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
300
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
301
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
302
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
303
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
304
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
305
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
306
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
307
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
308
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
309
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
310
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
311
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
312
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
313
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
314
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
315
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
316
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
317
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
318
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
319
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
320
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
321
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
323
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
325
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
327
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
328
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
329
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
330
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
331
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
332
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
333
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
334
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
336
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
339
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
341
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
342
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
343
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
344
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
345
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00007.safetensors",
346
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
347
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
348
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
349
+ "model.layers.28.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
350
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
351
+ "model.layers.28.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
352
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
353
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
354
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
355
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
356
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
357
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
358
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
359
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
360
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
361
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00007.safetensors",
362
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
363
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
364
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
365
+ "model.layers.29.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
366
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
367
+ "model.layers.29.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
368
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
369
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
370
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
371
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
372
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
373
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
374
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
375
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
376
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
377
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
378
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
379
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
380
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
381
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
382
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
383
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
384
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
385
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
386
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
387
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
388
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
389
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
390
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
391
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
392
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
393
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00007.safetensors",
394
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
395
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00007.safetensors",
396
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
397
+ "model.layers.30.mlp.gate_proj.weight_scale": "model-00003-of-00007.safetensors",
398
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
399
+ "model.layers.30.mlp.up_proj.weight_scale": "model-00003-of-00007.safetensors",
400
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
401
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
402
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
403
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
404
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
405
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
406
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
407
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
408
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
409
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
410
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
411
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
412
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
413
+ "model.layers.31.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
414
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
415
+ "model.layers.31.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
416
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
417
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
418
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00007.safetensors",
419
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
420
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00007.safetensors",
421
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
422
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00007.safetensors",
423
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
424
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00007.safetensors",
425
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
426
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
427
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
428
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
429
+ "model.layers.32.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
430
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
431
+ "model.layers.32.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
432
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
433
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
434
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
435
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
436
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
437
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
438
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
439
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
440
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
441
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
442
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
443
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
444
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
445
+ "model.layers.33.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
446
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
447
+ "model.layers.33.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
448
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
449
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
450
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
451
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
452
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
453
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
454
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
455
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
456
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
457
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
458
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
459
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
460
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
461
+ "model.layers.34.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
462
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
463
+ "model.layers.34.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
464
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
465
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
466
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
467
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
468
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
469
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
470
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
471
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
472
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
473
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
474
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
475
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
476
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
477
+ "model.layers.35.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
478
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
479
+ "model.layers.35.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
480
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
481
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
482
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
483
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
484
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
485
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
486
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
487
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
488
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
489
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
490
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
491
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
492
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
493
+ "model.layers.36.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
494
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
495
+ "model.layers.36.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
496
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
497
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
498
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
499
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
500
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
501
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
502
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
503
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
504
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
505
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
506
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
507
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
508
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
509
+ "model.layers.37.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
510
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
511
+ "model.layers.37.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
512
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
513
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
514
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
515
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
516
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
517
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
518
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
519
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
520
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
521
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00007.safetensors",
522
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
523
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
524
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
525
+ "model.layers.38.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
526
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
527
+ "model.layers.38.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
528
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
529
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
530
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
531
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
532
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
533
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
534
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
535
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
536
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
537
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00007.safetensors",
538
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
539
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
540
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
541
+ "model.layers.39.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
542
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
543
+ "model.layers.39.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
544
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
545
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
546
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
547
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
548
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
549
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
550
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
551
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
552
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
553
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
554
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
555
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
556
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
557
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
558
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
559
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
560
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
561
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
562
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
563
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
564
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
565
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
566
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
567
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
568
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
569
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00007.safetensors",
570
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
571
+ "model.layers.40.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
572
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
573
+ "model.layers.40.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
574
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
575
+ "model.layers.40.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
576
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
577
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
578
+ "model.layers.40.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
579
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
580
+ "model.layers.40.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
581
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
582
+ "model.layers.40.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
583
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
584
+ "model.layers.40.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
585
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00007.safetensors",
586
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
587
+ "model.layers.41.mlp.down_proj.weight_scale": "model-00004-of-00007.safetensors",
588
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
589
+ "model.layers.41.mlp.gate_proj.weight_scale": "model-00004-of-00007.safetensors",
590
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
591
+ "model.layers.41.mlp.up_proj.weight_scale": "model-00004-of-00007.safetensors",
592
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
593
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
594
+ "model.layers.41.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
595
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
596
+ "model.layers.41.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
597
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
598
+ "model.layers.41.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
599
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
600
+ "model.layers.41.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
601
+ "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
602
+ "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
603
+ "model.layers.42.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
604
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
605
+ "model.layers.42.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
606
+ "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
607
+ "model.layers.42.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
608
+ "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
609
+ "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
610
+ "model.layers.42.self_attn.k_proj.weight_scale": "model-00004-of-00007.safetensors",
611
+ "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
612
+ "model.layers.42.self_attn.o_proj.weight_scale": "model-00004-of-00007.safetensors",
613
+ "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
614
+ "model.layers.42.self_attn.q_proj.weight_scale": "model-00004-of-00007.safetensors",
615
+ "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
616
+ "model.layers.42.self_attn.v_proj.weight_scale": "model-00004-of-00007.safetensors",
617
+ "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
618
+ "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
619
+ "model.layers.43.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
620
+ "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
621
+ "model.layers.43.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
622
+ "model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
623
+ "model.layers.43.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
624
+ "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
625
+ "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
626
+ "model.layers.43.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
627
+ "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
628
+ "model.layers.43.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
629
+ "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
630
+ "model.layers.43.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
631
+ "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
632
+ "model.layers.43.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
633
+ "model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
634
+ "model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
635
+ "model.layers.44.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
636
+ "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
637
+ "model.layers.44.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
638
+ "model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
639
+ "model.layers.44.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
640
+ "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
641
+ "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
642
+ "model.layers.44.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
643
+ "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
644
+ "model.layers.44.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
645
+ "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
646
+ "model.layers.44.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
647
+ "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
648
+ "model.layers.44.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
649
+ "model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
650
+ "model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
651
+ "model.layers.45.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
652
+ "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
653
+ "model.layers.45.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
654
+ "model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
655
+ "model.layers.45.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
656
+ "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
657
+ "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
658
+ "model.layers.45.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
659
+ "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
660
+ "model.layers.45.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
661
+ "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
662
+ "model.layers.45.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
663
+ "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
664
+ "model.layers.45.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
665
+ "model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
666
+ "model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
667
+ "model.layers.46.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
668
+ "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
669
+ "model.layers.46.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
670
+ "model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
671
+ "model.layers.46.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
672
+ "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
673
+ "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
674
+ "model.layers.46.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
675
+ "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
676
+ "model.layers.46.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
677
+ "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
678
+ "model.layers.46.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
679
+ "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
680
+ "model.layers.46.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
681
+ "model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
682
+ "model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
683
+ "model.layers.47.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
684
+ "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
685
+ "model.layers.47.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
686
+ "model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
687
+ "model.layers.47.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
688
+ "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
689
+ "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
690
+ "model.layers.47.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
691
+ "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
692
+ "model.layers.47.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
693
+ "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
694
+ "model.layers.47.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
695
+ "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
696
+ "model.layers.47.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
697
+ "model.layers.48.input_layernorm.weight": "model-00005-of-00007.safetensors",
698
+ "model.layers.48.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
699
+ "model.layers.48.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
700
+ "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
701
+ "model.layers.48.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
702
+ "model.layers.48.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
703
+ "model.layers.48.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
704
+ "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
705
+ "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
706
+ "model.layers.48.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
707
+ "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
708
+ "model.layers.48.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
709
+ "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
710
+ "model.layers.48.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
711
+ "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
712
+ "model.layers.48.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
713
+ "model.layers.49.input_layernorm.weight": "model-00005-of-00007.safetensors",
714
+ "model.layers.49.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
715
+ "model.layers.49.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
716
+ "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
717
+ "model.layers.49.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
718
+ "model.layers.49.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
719
+ "model.layers.49.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
720
+ "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
721
+ "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
722
+ "model.layers.49.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
723
+ "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
724
+ "model.layers.49.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
725
+ "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
726
+ "model.layers.49.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
727
+ "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
728
+ "model.layers.49.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
729
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
730
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
731
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
732
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
733
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
734
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
735
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
736
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
737
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
738
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
739
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
740
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
741
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
742
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
743
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
744
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
745
+ "model.layers.50.input_layernorm.weight": "model-00005-of-00007.safetensors",
746
+ "model.layers.50.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
747
+ "model.layers.50.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
748
+ "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
749
+ "model.layers.50.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
750
+ "model.layers.50.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
751
+ "model.layers.50.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
752
+ "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
753
+ "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
754
+ "model.layers.50.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
755
+ "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
756
+ "model.layers.50.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
757
+ "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
758
+ "model.layers.50.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
759
+ "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
760
+ "model.layers.50.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
761
+ "model.layers.51.input_layernorm.weight": "model-00005-of-00007.safetensors",
762
+ "model.layers.51.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
763
+ "model.layers.51.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
764
+ "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
765
+ "model.layers.51.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
766
+ "model.layers.51.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
767
+ "model.layers.51.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
768
+ "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
769
+ "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
770
+ "model.layers.51.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
771
+ "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
772
+ "model.layers.51.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
773
+ "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
774
+ "model.layers.51.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
775
+ "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
776
+ "model.layers.51.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
777
+ "model.layers.52.input_layernorm.weight": "model-00005-of-00007.safetensors",
778
+ "model.layers.52.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
779
+ "model.layers.52.mlp.down_proj.weight_scale": "model-00005-of-00007.safetensors",
780
+ "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
781
+ "model.layers.52.mlp.gate_proj.weight_scale": "model-00005-of-00007.safetensors",
782
+ "model.layers.52.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
783
+ "model.layers.52.mlp.up_proj.weight_scale": "model-00005-of-00007.safetensors",
784
+ "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
785
+ "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
786
+ "model.layers.52.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
787
+ "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
788
+ "model.layers.52.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
789
+ "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
790
+ "model.layers.52.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
791
+ "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
792
+ "model.layers.52.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
793
+ "model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
794
+ "model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
795
+ "model.layers.53.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
796
+ "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
797
+ "model.layers.53.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
798
+ "model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
799
+ "model.layers.53.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
800
+ "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
801
+ "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
802
+ "model.layers.53.self_attn.k_proj.weight_scale": "model-00005-of-00007.safetensors",
803
+ "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
804
+ "model.layers.53.self_attn.o_proj.weight_scale": "model-00005-of-00007.safetensors",
805
+ "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
806
+ "model.layers.53.self_attn.q_proj.weight_scale": "model-00005-of-00007.safetensors",
807
+ "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
808
+ "model.layers.53.self_attn.v_proj.weight_scale": "model-00005-of-00007.safetensors",
809
+ "model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
810
+ "model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
811
+ "model.layers.54.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
812
+ "model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
813
+ "model.layers.54.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
814
+ "model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
815
+ "model.layers.54.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
816
+ "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
817
+ "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
818
+ "model.layers.54.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
819
+ "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
820
+ "model.layers.54.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
821
+ "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
822
+ "model.layers.54.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
823
+ "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
824
+ "model.layers.54.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
825
+ "model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors",
826
+ "model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
827
+ "model.layers.55.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
828
+ "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
829
+ "model.layers.55.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
830
+ "model.layers.55.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
831
+ "model.layers.55.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
832
+ "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
833
+ "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
834
+ "model.layers.55.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
835
+ "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
836
+ "model.layers.55.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
837
+ "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
838
+ "model.layers.55.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
839
+ "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
840
+ "model.layers.55.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
841
+ "model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
842
+ "model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
843
+ "model.layers.56.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
844
+ "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
845
+ "model.layers.56.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
846
+ "model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
847
+ "model.layers.56.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
848
+ "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
849
+ "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
850
+ "model.layers.56.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
851
+ "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
852
+ "model.layers.56.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
853
+ "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
854
+ "model.layers.56.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
855
+ "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
856
+ "model.layers.56.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
857
+ "model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
858
+ "model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
859
+ "model.layers.57.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
860
+ "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
861
+ "model.layers.57.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
862
+ "model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
863
+ "model.layers.57.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
864
+ "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
865
+ "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
866
+ "model.layers.57.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
867
+ "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
868
+ "model.layers.57.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
869
+ "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
870
+ "model.layers.57.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
871
+ "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
872
+ "model.layers.57.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
873
+ "model.layers.58.input_layernorm.weight": "model-00006-of-00007.safetensors",
874
+ "model.layers.58.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
875
+ "model.layers.58.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
876
+ "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
877
+ "model.layers.58.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
878
+ "model.layers.58.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
879
+ "model.layers.58.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
880
+ "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
881
+ "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
882
+ "model.layers.58.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
883
+ "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
884
+ "model.layers.58.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
885
+ "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
886
+ "model.layers.58.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
887
+ "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
888
+ "model.layers.58.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
889
+ "model.layers.59.input_layernorm.weight": "model-00006-of-00007.safetensors",
890
+ "model.layers.59.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
891
+ "model.layers.59.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
892
+ "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
893
+ "model.layers.59.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
894
+ "model.layers.59.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
895
+ "model.layers.59.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
896
+ "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
897
+ "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
898
+ "model.layers.59.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
899
+ "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
900
+ "model.layers.59.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
901
+ "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
902
+ "model.layers.59.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
903
+ "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
904
+ "model.layers.59.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
905
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
906
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
907
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
908
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
909
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
910
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
911
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
912
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
913
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
914
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
915
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
916
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
917
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
918
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
919
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
920
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
921
+ "model.layers.60.input_layernorm.weight": "model-00006-of-00007.safetensors",
922
+ "model.layers.60.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
923
+ "model.layers.60.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
924
+ "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
925
+ "model.layers.60.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
926
+ "model.layers.60.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
927
+ "model.layers.60.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
928
+ "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
929
+ "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
930
+ "model.layers.60.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
931
+ "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
932
+ "model.layers.60.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
933
+ "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
934
+ "model.layers.60.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
935
+ "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
936
+ "model.layers.60.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
937
+ "model.layers.61.input_layernorm.weight": "model-00006-of-00007.safetensors",
938
+ "model.layers.61.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
939
+ "model.layers.61.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
940
+ "model.layers.61.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
941
+ "model.layers.61.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
942
+ "model.layers.61.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
943
+ "model.layers.61.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
944
+ "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
945
+ "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
946
+ "model.layers.61.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
947
+ "model.layers.61.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
948
+ "model.layers.61.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
949
+ "model.layers.61.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
950
+ "model.layers.61.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
951
+ "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
952
+ "model.layers.61.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
953
+ "model.layers.62.input_layernorm.weight": "model-00006-of-00007.safetensors",
954
+ "model.layers.62.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
955
+ "model.layers.62.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
956
+ "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
957
+ "model.layers.62.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
958
+ "model.layers.62.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
959
+ "model.layers.62.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
960
+ "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
961
+ "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
962
+ "model.layers.62.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
963
+ "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
964
+ "model.layers.62.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
965
+ "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
966
+ "model.layers.62.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
967
+ "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
968
+ "model.layers.62.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
969
+ "model.layers.63.input_layernorm.weight": "model-00006-of-00007.safetensors",
970
+ "model.layers.63.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
971
+ "model.layers.63.mlp.down_proj.weight_scale": "model-00006-of-00007.safetensors",
972
+ "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
973
+ "model.layers.63.mlp.gate_proj.weight_scale": "model-00006-of-00007.safetensors",
974
+ "model.layers.63.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
975
+ "model.layers.63.mlp.up_proj.weight_scale": "model-00006-of-00007.safetensors",
976
+ "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
977
+ "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
978
+ "model.layers.63.self_attn.k_proj.weight_scale": "model-00006-of-00007.safetensors",
979
+ "model.layers.63.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
980
+ "model.layers.63.self_attn.o_proj.weight_scale": "model-00006-of-00007.safetensors",
981
+ "model.layers.63.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
982
+ "model.layers.63.self_attn.q_proj.weight_scale": "model-00006-of-00007.safetensors",
983
+ "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
984
+ "model.layers.63.self_attn.v_proj.weight_scale": "model-00006-of-00007.safetensors",
985
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
986
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
987
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
988
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
989
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
990
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
991
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
992
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
993
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
994
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
995
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
996
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
997
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
998
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
999
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
1000
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
1001
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors",
1002
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
1003
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00007.safetensors",
1004
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
1005
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00007.safetensors",
1006
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
1007
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00007.safetensors",
1008
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
1009
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
1010
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
1011
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
1012
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
1013
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
1014
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
1015
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
1016
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
1017
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
1018
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
1019
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00007.safetensors",
1020
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
1021
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00002-of-00007.safetensors",
1022
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
1023
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00002-of-00007.safetensors",
1024
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
1025
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
1026
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00007.safetensors",
1027
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
1028
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00007.safetensors",
1029
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
1030
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00007.safetensors",
1031
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
1032
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00007.safetensors",
1033
+ "model.norm.weight": "model-00006-of-00007.safetensors"
1034
+ }
1035
+ }
model.sig ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mediaType":"application/vnd.dev.sigstore.bundle.v0.3+json","verificationMaterial":{"certificate":{"rawBytes":"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"},"tlogEntries":[{"logIndex":"1353143825","logId":{"keyId":"wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="},"kindVersion":{"kind":"dsse","version":"0.0.1"},"integratedTime":"1776800005","inclusionPromise":{"signedEntryTimestamp":"MEYCIQCqUx/hv0TobV740xbYQOZhxITxG9f5Qvety2Vwd0JcpQIhAJ45mZ+zWFAbWD4s6XWy6+4qhkvsVwd5yzebWOmqicjL"},"inclusionProof":{"logIndex":"1231239563","rootHash":"HGKM6Dl1yCcR9qyHMbVvnWStkXlg9UlxIOtYEYAifvU=","treeSize":"1231239584","hashes":["uGP/9pVlzr1jnfSBTIDvHCx3IeBseaNtb37hBn/UrJg=","ny+omWprN4/fLzaXKuC/RC1HSg++6WLYN4Rd+wAm0Dk=","VJbBp6+SW8BMGq7DZeHm9vlniLqkvNAVQVslRa6ipjk=","8clg3P30xkO3/oivPeMO/Tsp/CAIWCYxJ0Fjz0oX6TU=","DUt8iHZkm9rK6V4XLNQgH35/aYhok1YobE+bkGzEe94=","8AXXajhJdZDQKA4Anf0zbsJbtDbwiWGt4ahHvRD7eSw=","kyc99pj6yr5c6cQb1iRFHKi+TT8trHvoCLcJhY7juZs=","t8csC4gx3DiWgHJv6woeDFqEWe1RZGhXHl8cNKuv6Kg=","WnVUdCxRwH88yGT2UzS0R7NIOtTcJuT+fXPXbdarMlc=","h0vSy7UlLLQXfGUXhtsXcfk6M++LnFpcJA3KjJXAe/c=","Ee0rG8HwzQ13TsKN3jiqnN6PUOrefyydhKIlW5hLas8=","et4q1LI5d2ghoX8/sEC/obBbPDNCsmK15oypur0/4uk=","gMqcPcRZq+qRpt2j2OrT6TYi0jJLQuxyfSCsDoyUYec=","7VGyDu6EqZ3w6qHPrlqezexOYVPJMZym3mFk1ula7AQ=","rHnyNltMkQ8pSBC0fcmsZJct4w7xKTvfhytE5NXvQMM=","7y22/OdvnNTJ3gzz57WEW6D/mmmrLXV0dVQyDwenx5A=","DOCeoSMovIvLExkhIvisow9AuNXgeWs4ECkyR6EcqYU="],"checkpoint":{"envelope":"rekor.sigstore.dev - 1193050959916656506\n1231239584\nHGKM6Dl1yCcR9qyHMbVvnWStkXlg9UlxIOtYEYAifvU=\n\n— rekor.sigstore.dev wNI9ajBGAiEAwzAgocN3eyFVCDkbKIi0XrMv6KOgtEpkigxgq8bReFQCIQDOqXD2TiCNQu5Y0TjTJn6MjLI32su6ieu5IeiBr8N0wA==\n"}},"canonicalizedBody":"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"}],"timestampVerificationData":{"rfc3161Timestamps":[{"signedTimestamp":"MIIE6TADAgEAMIIE4AYJKoZIhvcNAQcCoIIE0TCCBM0CAQMxDTALBglghkgBZQMEAgEwgcEGCyqGSIb3DQEJEAEEoIGxBIGuMIGrAgEBBgkrBgEEAYO/MAIwMTANBglghkgBZQMEAgEFAAQgH88jhYN65/9AAXSts86tyi1bRg5lczUh5Wj8fdb0WnICFFc4vCYveaYsgwTtDiZCqRm4n5joGA8yMDI2MDQyMTE5MzMyNFowAwIBAQIIFqO0zwNVz1egMqQwMC4xFTATBgNVBAoTDHNpZ3N0b3JlLmRldjEVMBMGA1UEAxMMc2lnc3RvcmUtdHNhoIICFDCCAhAwggGWoAMCAQICFDoTVC8MkGHuvMFDL8uKjosqI4sMMAoGCCqGSM49BAMDMDkxFTATBgNVBAoTDHNpZ3N0b3JlLmRldjEgMB4GA1UEAxMXc2lnc3RvcmUtdHNhLXNlbGZzaWduZWQwHhcNMjUwNDA4MDY1OTQzWhcNMzUwNDA2MDY1OTQzWjAuMRUwEwYDVQQKEwxzaWdzdG9yZS5kZXYxFTATBgNVBAMTDHNpZ3N0b3JlLXRzYTB2MBAGByqGSM49AgEGBSuBBAAiA2IABOK2tmfISjYoNk/ZBYwgE6Bht9I5MvlkL9wcy/pir4dUijUf1MLsLHzQoOLK8qGAHfBOorKL1QNzOGqDXZvUA4udGfJ0xMr6oHwz7UyMFyLX4lvwBX9Ve7sJG5AKI9McXKNqMGgwDgYDVR0PAQH/BAQDAgeAMB0GA1UdDgQWBBSJ/XlDh8/QZUbDAkbHLHNbfbTrAzAfBgNVHSMEGDAWgBSY7AHvf7tR/9SVHm+KiJhTB4nOvzAWBgNVHSUBAf8EDDAKBggrBgEFBQcDCDAKBggqhkjOPQQDAwNoADBlAjA7abFf+imjtKshf1DLF9mklFykBXaBk6bUBnNH7atXLLpRzxhunbJsjDXdyQfhtxECMQDmo7wXI6SZim+Db/tk2qI/FHOfm+ooehVwgiq2kqrqXtO86rMDHFyU3tXBMbx775cxggHbMIIB1wIBATBRMDkxFTATBgNVBAoTDHNpZ3N0b3JlLmRldjEgMB4GA1UEAxMXc2lnc3RvcmUtdHNhLXNlbGZzaWduZWQCFDoTVC8MkGHuvMFDL8uKjosqI4sMMAsGCWCGSAFlAwQCAaCB/DAaBgkqhkiG9w0BCQMxDQYLKoZIhvcNAQkQAQQwHAYJKoZIhvcNAQkFMQ8XDTI2MDQyMTE5MzMyNFowLwYJKoZIhvcNAQkEMSIEIN//sT3WaYWCGflMUvYNq4/nn34MMBnMpmweAhm9xzRLMIGOBgsqhkiG9w0BCRACLzF/MH0wezB5BCCF+Se8B6tiysO0Q1bBDvyBssaIP9p6uebYcNnROs0FtzBVMD2kOzA5MRUwEwYDVQQKEwxzaWdzdG9yZS5kZXYxIDAeBgNVBAMTF3NpZ3N0b3JlLXRzYS1zZWxmc2lnbmVkAhQ6E1QvDJBh7rzBQy/Lio6LKiOLDDAKBggqhkjOPQQDAgRnMGUCMClbdrSv5YotXSTz+XI8ji2zrHZpz+OMpQGrD8xmLud79mMmjwVCghAqPp4dO06JmwIxAPJQao2m9bWgPwQuW5KK1mflOtv/xE40rLGia4hKTdpceJ9ySwnBCBtsq6VIhNULJw=="}]}},"dsseEnvelope":{"payload":"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","payloadType":"application/vnd.in-toto+json","signatures":[{"sig":"MEUCIHN2Pc6VnLcrc5pAVf0kpwyGmKVFmojzdaoRZeuz1ZM1AiEA8SRbZ1+4OdhMi0xNPFS6kCT4d/KfD7ExUeitEUCfSvg="}]}}
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: FP8_DYNAMIC
7
+ bypass_divisibility_checks: false
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|end_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100257": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "100261": {
46
+ "content": "<|fim_pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "100262": {
54
+ "content": "<|filename|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "100263": {
62
+ "content": "<|reponame|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "100264": {
70
+ "content": "<|start_of_role|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<|end_of_role|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<|unused_1|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "100267": {
94
+ "content": "<|start_of_plugin|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "100268": {
102
+ "content": "<|end_of_plugin|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "100269": {
110
+ "content": "<|unk|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "100270": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "100271": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "100272": {
134
+ "content": "<tool_response>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "100273": {
142
+ "content": "</tool_response>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "100274": {
150
+ "content": "<think>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "100275": {
158
+ "content": "</think>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "100276": {
166
+ "content": "<think_on>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<think_off>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "100278": {
182
+ "content": "<schema>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "100279": {
190
+ "content": "</schema>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100280": {
198
+ "content": "<tools>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100281": {
206
+ "content": "</tools>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "100282": {
214
+ "content": "<documents>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "100283": {
222
+ "content": "</documents>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "100284": {
230
+ "content": "<|unused_15|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "100285": {
238
+ "content": "<|unused_16|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "100286": {
246
+ "content": "<|unused_17|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "100287": {
254
+ "content": "<|unused_18|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "100288": {
262
+ "content": "<|unused_19|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "100289": {
270
+ "content": "<|unused_20|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "100290": {
278
+ "content": "<|unused_21|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "100291": {
286
+ "content": "<|unused_22|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "100292": {
294
+ "content": "<|unused_23|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "100293": {
302
+ "content": "<|unused_24|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "100294": {
310
+ "content": "<|unused_25|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "100295": {
318
+ "content": "<|unused_26|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "100296": {
326
+ "content": "<|unused_27|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "100297": {
334
+ "content": "<|unused_28|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "100298": {
342
+ "content": "<|unused_29|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "100299": {
350
+ "content": "<|unused_30|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "100300": {
358
+ "content": "<|unused_31|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "100301": {
366
+ "content": "<|unused_32|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "100302": {
374
+ "content": "<|unused_33|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "100303": {
382
+ "content": "<|unused_34|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "100304": {
390
+ "content": "<|unused_35|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "100305": {
398
+ "content": "<|unused_36|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "100306": {
406
+ "content": "<|unused_37|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "100307": {
414
+ "content": "<|unused_38|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "100308": {
422
+ "content": "<|unused_39|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "100309": {
430
+ "content": "<|unused_40|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "100310": {
438
+ "content": "<|unused_41|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "100311": {
446
+ "content": "<|unused_42|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "100312": {
454
+ "content": "<|unused_43|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "100313": {
462
+ "content": "<|unused_44|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "100314": {
470
+ "content": "<|unused_45|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "100315": {
478
+ "content": "<|unused_46|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "100316": {
486
+ "content": "<|unused_47|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "100317": {
494
+ "content": "<|unused_48|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "100318": {
502
+ "content": "<|unused_49|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "100319": {
510
+ "content": "<|unused_50|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "100320": {
518
+ "content": "<|unused_51|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "100321": {
526
+ "content": "<|unused_52|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "100322": {
534
+ "content": "<|unused_53|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "100323": {
542
+ "content": "<|unused_54|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "100324": {
550
+ "content": "<|unused_55|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "100325": {
558
+ "content": "<|unused_56|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "100326": {
566
+ "content": "<|unused_57|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "100327": {
574
+ "content": "<|unused_58|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "100328": {
582
+ "content": "<|unused_59|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "100329": {
590
+ "content": "<|unused_60|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "100330": {
598
+ "content": "<|unused_61|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "100331": {
606
+ "content": "<|unused_62|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "100332": {
614
+ "content": "<|unused_63|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "100333": {
622
+ "content": "<|unused_64|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "100334": {
630
+ "content": "<|unused_65|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "100335": {
638
+ "content": "<|unused_66|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "100336": {
646
+ "content": "<|unused_67|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "100337": {
654
+ "content": "<|unused_68|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "100338": {
662
+ "content": "<|unused_69|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "100339": {
670
+ "content": "<|unused_70|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "100340": {
678
+ "content": "<|unused_71|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "100341": {
686
+ "content": "<|unused_72|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "100342": {
694
+ "content": "<|unused_73|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "100343": {
702
+ "content": "<|unused_74|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "100344": {
710
+ "content": "<|unused_75|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "100345": {
718
+ "content": "<|unused_76|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "100346": {
726
+ "content": "<|unused_77|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "100347": {
734
+ "content": "<|unused_78|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "100348": {
742
+ "content": "<|unused_79|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "100349": {
750
+ "content": "<|unused_80|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "100350": {
758
+ "content": "<|unused_81|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "100351": {
766
+ "content": "<|unused_82|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ }
773
+ },
774
+ "bos_token": "<|end_of_text|>",
775
+ "clean_up_tokenization_spaces": false,
776
+ "eos_token": "<|end_of_text|>",
777
+ "extra_special_tokens": {},
778
+ "model_max_length": 1000000000000000019884624838656,
779
+ "pad_token": "<|pad|>",
780
+ "padding_side": "left",
781
+ "tokenizer_class": "GPT2Tokenizer",
782
+ "unk_token": "<|unk|>"
783
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff