Hugging Face's logo

openbmb
/
MiniCPM5-1B-MLX

Text Generation
Transformers
Safetensors
English
Chinese
llama
minicpm
minicpm5
long-context
tool-calling
on-device
edge-ai
conversational
text-generation-inference
4-bit precision
Model card Files
xet
 Community
BigDong commited on
Commit
92b4f50
·
1 Parent(s): 6c6ac87

upload model

Browse files
Files changed (7) hide show
  1. chat_template.jinja +179 -0
  2. config.json +40 -0
  3. generation_config.json +10 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +567 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +15 -0
chat_template.jinja ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}{%- if tools %}
2
+ {%- set tool_definitions %}
3
+ {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
4
+ {%- for tool in tools %}
5
+ {{- "\n" }}
6
+ {{- tool | tojson(ensure_ascii=False) }}
7
+ {%- endfor %}
8
+ {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
9
+ {%- endset %}
10
+
11
+ {{- '<|im_start|>system\n' }}
12
+ {%- if messages[0].role == 'system' %}
13
+ {%- if '<tool_def_sep>' in messages[0].content %}
14
+ {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
15
+ {%- else %}
16
+ {{- messages[0].content + '\n\n' + tool_definitions }}
17
+ {%- endif %}
18
+ {%- else %}
19
+ {{- tool_definitions.lstrip() }}
20
+ {%- endif %}
21
+ {{- '<|im_end|>\n' }}
22
+ {%- else %}
23
+ {%- if messages[0].role == 'system' %}
24
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
25
+ {%- endif %}
26
+ {%- endif %}
27
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
28
+ {%- for message in messages[::-1] %}
29
+ {%- set index = (messages|length - 1) - loop.index0 %}
30
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
31
+ {%- set ns.multi_step_tool = false %}
32
+ {%- set ns.last_query_index = index %}
33
+ {%- endif %}
34
+ {%- endfor %}
35
+ {%- for message in messages %}
36
+ {%- if message.content is string %}
37
+ {%- set content = message.content %}
38
+ {%- else %}
39
+ {%- set content = '' %}
40
+ {%- endif %}
41
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
42
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
43
+ {%- elif message.role == "assistant" %}
44
+ {%- set reasoning_content = '' %}
45
+ {%- if message.reasoning_content is string %}
46
+ {%- set reasoning_content = message.reasoning_content %}
47
+ {%- else %}
48
+ {%- if '</think>' in content %}
49
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
50
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
51
+ {%- endif %}
52
+ {%- endif %}
53
+
54
+ {%- if message.tool_calls %}
55
+ {%- set content_parts = content.split('<tool_sep>') %}
56
+ {%- set processed_content = content_parts[0] %}
57
+ {%- set tool_calls_count = message.tool_calls|length %}
58
+ {%- set tool_sep_count = content_parts|length - 1 %}
59
+ {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
60
+
61
+ {%- for i in range(1, content_parts|length) %}
62
+ {%- set tool_index = i - 1 %}
63
+ {%- if tool_index < tool_calls_count %}
64
+ {%- set tool_call = message.tool_calls[tool_index] %}
65
+ {%- if tool_call.function %}
66
+ {%- set tool_call = tool_call.function %}
67
+ {%- endif %}
68
+ {%- set single_tool_xml %}
69
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
70
+ {%- if tool_call.arguments %}
71
+ {%- set args_dict = tool_call.arguments %}
72
+ {%- for param_name, param_value in args_dict.items() %}
73
+ {{- '<param name="' ~ param_name ~ '">' }}
74
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
75
+ {{- '<![CDATA[' + param_value + ']]>' }}
76
+ {%- else %}
77
+ {{- param_value }}
78
+ {%- endif %}
79
+ {{- '</param>' }}
80
+ {%- endfor %}
81
+ {%- endif %}
82
+ {{- '</function>' }}
83
+ {%- endset %}
84
+ {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
85
+ {%- else %}
86
+ {%- set processed_content = processed_content + content_parts[i] %}
87
+ {%- endif %}
88
+ {%- endfor %}
89
+
90
+ {%- if tool_calls_count > tool_sep_count %}
91
+ {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
92
+ {%- set tool_call = message.tool_calls[remaining_index] %}
93
+ {%- if tool_call.function %}
94
+ {%- set tool_call = tool_call.function %}
95
+ {%- endif %}
96
+ {%- set remaining_tool_xml %}
97
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
98
+ {%- if tool_call.arguments %}
99
+ {%- set args_dict = tool_call.arguments %}
100
+ {%- for param_name, param_value in args_dict.items() %}
101
+ {{- '<param name="' ~ param_name ~ '">' }}
102
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
103
+ {{- '<![CDATA[' + param_value + ']]>' }}
104
+ {%- else %}
105
+ {{- param_value }}
106
+ {%- endif %}
107
+ {{- '</param>' }}
108
+ {%- endfor %}
109
+ {%- endif %}
110
+ {{- '</function>' }}
111
+ {%- endset %}
112
+ {%- set processed_content = processed_content + remaining_tool_xml %}
113
+ {%- endfor %}
114
+ {%- endif %}
115
+
116
+ {%- set content = processed_content %}
117
+ {%- endif %}
118
+
119
+ {%- if loop.index0 > ns.last_query_index %}
120
+ {%- if reasoning_content %}
121
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
122
+ {%- else %}
123
+ {{- '<|im_start|>' + message.role + '\n' + content }}
124
+ {%- endif %}
125
+ {%- else %}
126
+ {{- '<|im_start|>' + message.role + '\n' + content }}
127
+ {%- endif %}
128
+
129
+ {%- if message.tool_calls and not has_tool_sep %}
130
+ {%- for tool_call in message.tool_calls %}
131
+ {%- if (loop.first and content) or (not loop.first) %}
132
+ {{- '\n' }}
133
+ {%- endif %}
134
+ {%- if tool_call.function %}
135
+ {%- set tool_call = tool_call.function %}
136
+ {%- endif %}
137
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
138
+ {%- if tool_call.arguments %}
139
+ {%- set args_dict = tool_call.arguments %}
140
+ {%- for param_name, param_value in args_dict.items() %}
141
+ {{- '<param name="' ~ param_name ~ '">' }}
142
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
143
+ {{- '<![CDATA[' + param_value + ']]>' }}
144
+ {%- else %}
145
+ {{- param_value }}
146
+ {%- endif %}
147
+ {{- '</param>' }}
148
+ {%- endfor %}
149
+ {%- endif %}
150
+ {{- '</function>' }}
151
+ {%- endfor %}
152
+ {%- endif %}
153
+ {{- '<|im_end|>\n' }}
154
+ {%- elif message.role == "tool" %}
155
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
156
+ {{- '<|im_start|>user' }}
157
+ {%- endif %}
158
+ {{- '\n<tool_response>\n' }}
159
+ {%- if message.content is string %}
160
+ {{- content }}
161
+ {%- else %}
162
+ {{- message.content | tojson(ensure_ascii=False) }}
163
+ {%- endif %}
164
+ {{- '\n</tool_response>' }}
165
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
166
+ {{- '<|im_end|>\n' }}
167
+ {%- endif %}
168
+ {%- endif %}
169
+ {%- endfor %}
170
+ {%- if add_generation_prompt %}
171
+ {{- '<|im_start|>assistant\n' }}
172
+ {%- if enable_thinking is defined %}
173
+ {%- if enable_thinking is false %}
174
+ {{- '<think>\n\n</think>\n\n' }}
175
+ {%- elif enable_thinking is true %}
176
+ {{- '<think>\n' }}
177
+ {%- endif %}
178
+ {%- endif %}
179
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MiniCPM5-1B-MLX",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": [
8
+ 1,
9
+ 130073
10
+ ],
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4608,
16
+ "max_position_embeddings": 131072,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 2,
21
+ "pad_token_id": 1,
22
+ "quantization": {
23
+ "group_size": 64,
24
+ "bits": 4,
25
+ "mode": "affine"
26
+ },
27
+ "quantization_config": {
28
+ "group_size": 64,
29
+ "bits": 4,
30
+ "mode": "affine"
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": null,
34
+ "rope_theta": 5000000,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "5.6.2",
38
+ "use_cache": true,
39
+ "vocab_size": 130560
40
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [1, 130073],
5
+ "pad_token_id": 1,
6
+ "do_sample": true,
7
+ "temperature": 0.9,
8
+ "top_p": 0.95,
9
+ "transformers_version": "5.6.2"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23e0c5c79944a0b2cc92cb9ab79376b4dce41e2312383727e21ee43fe19cb4f
3
+ size 608026621
model.safetensors.index.json ADDED
@@ -0,0 +1,567 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 607964160,
4
+ "total_parameters": 1080632832
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model.safetensors",
8
+ "lm_head.scales": "model.safetensors",
9
+ "lm_head.weight": "model.safetensors",
10
+ "model.embed_tokens.biases": "model.safetensors",
11
+ "model.embed_tokens.scales": "model.safetensors",
12
+ "model.embed_tokens.weight": "model.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
20
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
21
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
22
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
23
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
24
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
25
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
26
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
27
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
28
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
29
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
30
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
31
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
32
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
33
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
34
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
35
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
36
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
37
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
38
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
39
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
40
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
41
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
42
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
43
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
44
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
45
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
46
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
47
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
48
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
49
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
50
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
51
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
52
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
53
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
54
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
55
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
56
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
57
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
58
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
59
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
60
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
61
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
62
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
63
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
64
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
65
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
66
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
67
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
68
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
69
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
70
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
71
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
72
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
73
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
74
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
75
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
76
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
77
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
78
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
79
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
80
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
81
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
82
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
83
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
84
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
85
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
86
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
87
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
88
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
89
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
90
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
91
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
92
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
93
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
94
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
95
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
96
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
97
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
98
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
99
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
100
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
101
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
102
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
103
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
104
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
105
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
106
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
107
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
108
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
109
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
110
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
111
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
112
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
113
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
114
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
115
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
116
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
117
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
118
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
119
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
120
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
121
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
122
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
123
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
124
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
125
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
126
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
127
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
128
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
129
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
130
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
131
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
132
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
133
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
134
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
135
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
136
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
137
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
138
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
139
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
140
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
141
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
142
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
143
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
144
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
145
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
146
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
147
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
148
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
149
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
150
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
151
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
152
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
153
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
154
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
155
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
156
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
157
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
158
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
159
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
160
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
161
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
162
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
163
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
164
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
165
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
166
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
167
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
168
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
169
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
170
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
171
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
172
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
173
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
174
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
175
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
176
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
177
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
178
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
179
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
180
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
181
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
182
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
183
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
184
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
185
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
186
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
187
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
188
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
189
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
190
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
191
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
192
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
193
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
194
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
195
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
196
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
197
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
198
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
199
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
200
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
201
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
202
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
203
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
204
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
205
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
206
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
207
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
208
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
209
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
210
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
211
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
212
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
213
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
214
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
215
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
216
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
217
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
218
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
219
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
220
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
221
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
222
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
223
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
224
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
225
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
226
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
227
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
228
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
229
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
230
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
231
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
232
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
233
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
234
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
235
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
236
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
237
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
238
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
239
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
240
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
241
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
242
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
243
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
244
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
245
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
246
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
247
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
248
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
249
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
250
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
251
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
252
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
253
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
254
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
255
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
256
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
257
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
258
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
259
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
260
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
261
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
262
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
263
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
264
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
265
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
266
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
267
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
268
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
269
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
270
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
271
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
272
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
273
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
274
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
275
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
276
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
277
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
278
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
279
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
280
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
281
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
282
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
283
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
284
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
285
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
286
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
287
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
288
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
289
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
290
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
291
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
292
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
293
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
294
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
295
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
296
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
297
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
298
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
299
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
300
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
301
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
302
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
303
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
304
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
305
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
306
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
307
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
308
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
309
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
310
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
311
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
312
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
313
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
314
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
315
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
316
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
317
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
318
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
319
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
320
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
321
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
322
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
323
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
324
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
325
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
326
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
327
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
328
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
329
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
330
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
331
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
332
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
333
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
334
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
335
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
336
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
337
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
338
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
339
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
340
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
341
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
342
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
343
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
344
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
345
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
346
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
347
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
348
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
349
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
350
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
351
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
352
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
353
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
354
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
355
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
356
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
357
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
358
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
359
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
360
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
361
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
362
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
363
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
364
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
365
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
366
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
367
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
368
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
369
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
370
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
371
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
372
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
373
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
374
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
375
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
376
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
377
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
378
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
379
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
380
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
381
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
382
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
383
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
384
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
385
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
386
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
387
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
388
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
389
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
390
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
391
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
392
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
393
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
394
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
395
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
396
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
397
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
398
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
399
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
400
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
401
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
402
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
403
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
404
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
405
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
406
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
407
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
408
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
409
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
410
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
411
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
412
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
413
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
414
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
415
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
416
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
417
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
418
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
419
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
420
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
421
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
422
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
423
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
424
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
425
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
426
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
427
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
428
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
429
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
430
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
431
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
432
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
433
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
434
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
435
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
436
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
437
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
438
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
439
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
440
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
441
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
442
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
443
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
444
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
445
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
446
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
447
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
448
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
449
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
450
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
451
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
452
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
453
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
454
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
455
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
456
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
457
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
458
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
459
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
460
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
461
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
462
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
463
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
464
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
465
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
466
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
467
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
468
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
469
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
470
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
471
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
472
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
473
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
474
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
475
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
476
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
477
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
478
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
479
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
480
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
481
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
482
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
483
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
484
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
485
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
486
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
487
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
488
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
489
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
490
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
491
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
492
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
493
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
494
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
495
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
496
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
497
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
498
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
499
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
500
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
501
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
502
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
503
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
504
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
505
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
506
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
507
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
508
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
509
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
510
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
511
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
512
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
513
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
514
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
515
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
516
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
517
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
518
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
519
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
520
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
521
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
522
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
523
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
524
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
525
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
526
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
527
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
528
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
529
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
530
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
531
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
532
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
533
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
534
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
535
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
536
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
537
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
538
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
539
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
540
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
541
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
542
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
543
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
544
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
545
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
546
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
547
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
548
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
549
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
550
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
551
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
552
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
553
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
554
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
555
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
556
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
557
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
558
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
559
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
560
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
561
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
562
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
563
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
564
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
565
+ "model.norm.weight": "model.safetensors"
566
+ }
567
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "</s>",
11
+ "spaces_between_special_tokens": false,
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": "<unk>",
14
+ "use_default_system_prompt": false
15
+ }