prince-canuma commited on
Commit
16b359a
·
verified ·
1 Parent(s): 2f28015

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-generation
3
+ license: mit
4
+ library_name: mlx
5
+ base_model: MiniMaxAI/MiniMax-M2
6
+ tags:
7
+ - mlx
8
+ ---
9
+
10
+ # mlx-community/MiniMax-M2-3bit
11
+
12
+ This model [mlx-community/MiniMax-M2-3bit](https://huggingface.co/mlx-community/MiniMax-M2-3bit) was
13
+ converted to MLX format from [MiniMaxAI/MiniMax-M2](https://huggingface.co/MiniMaxAI/MiniMax-M2)
14
+ using mlx-lm version **0.28.4**.
15
+
16
+ ## Use with mlx
17
+
18
+ ```bash
19
+ pip install mlx-lm
20
+ ```
21
+
22
+ ```python
23
+ from mlx_lm import load, generate
24
+
25
+ model, tokenizer = load("mlx-community/MiniMax-M2-3bit")
26
+
27
+ prompt = "hello"
28
+
29
+ if tokenizer.chat_template is not None:
30
+ messages = [{"role": "user", "content": prompt}]
31
+ prompt = tokenizer.apply_chat_template(
32
+ messages, add_generation_prompt=True
33
+ )
34
+
35
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
36
+ ```
added_tokens.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</minimax:tool_call>": 200053,
3
+ "</think>": 200051,
4
+ "<add_file>": 200036,
5
+ "<code_context>": 200043,
6
+ "<code_interpreter>": 200023,
7
+ "<commit_after>": 200018,
8
+ "<commit_before>": 200016,
9
+ "<commit_message>": 200040,
10
+ "<commit_msg>": 200017,
11
+ "<delete_file>": 200037,
12
+ "<edit_file>": 200039,
13
+ "<empty_output>": 200015,
14
+ "<empty_source_file>": 200041,
15
+ "<file_content>": 200044,
16
+ "<file_sep>": 200049,
17
+ "<filename>": 200006,
18
+ "<filepath>": 200048,
19
+ "<fim_middle>": 200002,
20
+ "<fim_pad>": 200004,
21
+ "<fim_prefix>": 200001,
22
+ "<fim_suffix>": 200003,
23
+ "<function_call>": 200022,
24
+ "<gh_stars>": 200007,
25
+ "<issue_closed>": 200010,
26
+ "<issue_comment>": 200009,
27
+ "<issue_start>": 200008,
28
+ "<jupyter_code>": 200013,
29
+ "<jupyter_error>": 200035,
30
+ "<jupyter_output>": 200014,
31
+ "<jupyter_start>": 200011,
32
+ "<jupyter_text>": 200012,
33
+ "<minimax:tool_call>": 200052,
34
+ "<pr_start>": 200046,
35
+ "<rename_file>": 200038,
36
+ "<repo_struct>": 200042,
37
+ "<reponame>": 200005,
38
+ "<review_comment>": 200047,
39
+ "<source_files>": 200045,
40
+ "<think>": 200050,
41
+ "[e~[": 200020,
42
+ "]!d~[": 200021,
43
+ "]!p~[": 200000,
44
+ "]<]end of image[>[": 200030,
45
+ "]<]end of speech[>[": 200028,
46
+ "]<]end of video[>[": 200032,
47
+ "]<]image[>[": 200025,
48
+ "]<]speech[>[": 200024,
49
+ "]<]start of image[>[": 200029,
50
+ "]<]start of speech[>[": 200027,
51
+ "]<]start of video[>[": 200031,
52
+ "]<]video[>[": 200026,
53
+ "]<]vision pad[>[": 200033,
54
+ "]~!b[": 200034,
55
+ "]~b]": 200019
56
+ }
chat_template.jinja ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ----------‑‑‑ special token variables ‑‑‑---------- #}
2
+ {%- set toolcall_begin_token = '<minimax:tool_call>' -%}
3
+ {%- set toolcall_end_token = '</minimax:tool_call>' -%}
4
+ {#- Tool Rendering Functions ============================================== -#}
5
+ {%- macro render_tool_namespace(namespace_name, tool_list) -%}
6
+ {%- for tool in tool_list -%}
7
+ <tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
8
+ {% endfor -%}
9
+ {%- endmacro -%}
10
+ {%- macro visible_text(content) -%}
11
+ {%- if content is string -%}
12
+ {{ content }}
13
+ {%- elif content is iterable and content is not mapping -%}
14
+ {%- for item in content -%}
15
+ {%- if item is mapping and item.type == 'text' -%}
16
+ {{- item.text }}
17
+ {%- elif item is string -%}
18
+ {{- item }}
19
+ {%- endif -%}
20
+ {%- endfor -%}
21
+ {%- else -%}
22
+ {{- content }}
23
+ {%- endif -%}
24
+ {%- endmacro -%}
25
+ {#- System Message Construction ============================================ -#}
26
+ {%- macro build_system_message(system_message) -%}
27
+ {%- if system_message and system_message.content -%}
28
+ {{- visible_text(system_message.content) }}
29
+ {%- else -%}
30
+ {%- if model_identity is not defined -%}
31
+ {%- set model_identity = "You are a helpful assistant." -%}
32
+ {%- endif -%}
33
+ {{- model_identity }}
34
+ {%- endif -%}
35
+
36
+ {#- Handle current_date -#}
37
+ {%- if system_message and system_message.current_date -%}
38
+ {{- '\n' ~ 'Current date: ' + system_message.current_date }}
39
+ {%- endif -%}
40
+ {#- Handle current_location -#}
41
+ {%- if system_message and system_message.current_location -%}
42
+ {{- '\n' ~ 'Current location: ' + system_message.current_location }}
43
+ {%- endif -%}
44
+ {%- endmacro -%}
45
+ {#- Main Template Logic ================================================= -#}
46
+ {#- Extract system message (only first message if it's system) -#}
47
+ {%- set system_message = none -%}
48
+ {%- set conversation_messages = messages -%}
49
+ {%- if messages and messages[0].role == "system" -%}
50
+ {%- set system_message = messages[0] -%}
51
+ {%- set conversation_messages = messages[1:] -%}
52
+ {%- endif -%}
53
+ {#- Get the last user message turn, for interleved thinking -#}
54
+ {%- set ns = namespace(last_user_index=-1) %}
55
+ {% for m in conversation_messages %}
56
+ {%- if m.role == 'user' %}
57
+ {% set ns.last_user_index = loop.index0 -%}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {#- Render system message -#}
61
+ {{- ']~!b[' ~ ']~b]system' ~ '\n' }}
62
+ {{- build_system_message(system_message) }}
63
+ {#- Render tools if available -#}
64
+ {%- if tools -%}
65
+ {{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
66
+ {{- '\n' ~ '<tools>' ~ '\n' }}
67
+ {{- render_tool_namespace("functions", tools) }}
68
+ {{- '</tools>' ~ '\n\n' }}
69
+ {{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\n' }}
70
+ {{- '\n' ~ toolcall_begin_token }}
71
+ <invoke name="tool-name-1">
72
+ <parameter name="param-key-1">param-value-1</parameter>
73
+ <parameter name="param-key-2">param-value-2</parameter>
74
+ ...
75
+ </invoke>
76
+ {{- '\n' ~ toolcall_end_token }}
77
+ {%- endif -%}
78
+ {{- '[e~[\n' }}
79
+
80
+ {#- Render messages -#}
81
+ {%- set last_tool_call = namespace(name=none) -%}
82
+ {%- for message in conversation_messages -%}
83
+ {%- if message.role == 'assistant' -%}
84
+ {#- Only render reasoning_content if no user message follows -#}
85
+ {{- ']~b]ai' ~ '\n' }}
86
+
87
+ {%- set reasoning_content = '' %}
88
+ {%- set content = visible_text(message.content) %}
89
+ {%- if message.reasoning_content is string %}
90
+ {%- set reasoning_content = message.reasoning_content %}
91
+ {%- else %}
92
+ {%- if '</think>' in content %}
93
+ {%- set reasoning_content = content.split('</think>')[0].strip('\n').split('<think>')[-1].strip('\n') %}
94
+ {%- set content = content.split('</think>')[-1].strip('\n') %}
95
+ {%- endif %}
96
+ {%- endif %}
97
+ {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
98
+ {{- '<think>' ~ '\n' ~ reasoning_content ~ '\n' ~ '</think>' ~ '\n\n' }}
99
+ {%- endif -%}
100
+ {%- if content -%}
101
+ {{- content }}
102
+ {%- endif -%}
103
+ {%- if message.tool_calls -%}
104
+ {{- '\n' ~ toolcall_begin_token ~ '\n' }}
105
+
106
+ {%- for tool_call in message.tool_calls -%}
107
+ {%- if tool_call.function %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {{- '<invoke name="' + tool_call.name + '">' }}
111
+ {% set _args = tool_call.arguments %}
112
+ {%- for k, v in _args.items() %}
113
+ {{- '<parameter name="' + k + '">' }}
114
+ {{- v | tojson(ensure_ascii=False) if v is not string else v }}
115
+ {{- '</parameter>' }}
116
+ {% endfor %}
117
+ {{- '</invoke>' ~ '\n' }}
118
+ {%- endfor -%}
119
+
120
+ {{- toolcall_end_token}}
121
+ {%- set last_tool_call.name = message.tool_calls[-1].name -%}
122
+ {%- else -%}
123
+ {%- set last_tool_call.name = none -%}
124
+ {%- endif -%}
125
+ {{- '[e~[' ~ '\n' }}
126
+
127
+ {%- elif message.role == 'tool' -%}
128
+ {%- if last_tool_call.name is none -%}
129
+ {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
130
+ {%- endif -%}
131
+ {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
132
+ {{- ']~b]tool' }}
133
+ {%- endif -%}
134
+ {%- if message.content is string -%}
135
+ {{- '\n<response>' }}
136
+ {{- message.content }}
137
+ {{- '</response>' }}
138
+ {%- else -%}
139
+ {%- for tr in message.content -%}
140
+ {{- '\n<response>' }}
141
+ {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
142
+ {{- '\n</response>' }}
143
+ {%- endfor -%}
144
+ {%- endif -%}
145
+ {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
146
+ {{- '[e~[\n' -}}
147
+ {%- endif -%}
148
+
149
+ {%- elif message.role == 'user' -%}
150
+ {{- ']~b]user' ~ '\n' }}
151
+ {{- visible_text(message.content) }}
152
+ {{- '[e~[' ~ '\n' }}
153
+ {%- endif -%}
154
+ {%- endfor -%}
155
+
156
+ {#- Generation prompt -#}
157
+ {%- if add_generation_prompt -%}
158
+ {{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
159
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,614 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MiniMaxM2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "attn_type_list": [
7
+ 1,
8
+ 1,
9
+ 1,
10
+ 1,
11
+ 1,
12
+ 1,
13
+ 1,
14
+ 1,
15
+ 1,
16
+ 1,
17
+ 1,
18
+ 1,
19
+ 1,
20
+ 1,
21
+ 1,
22
+ 1,
23
+ 1,
24
+ 1,
25
+ 1,
26
+ 1,
27
+ 1,
28
+ 1,
29
+ 1,
30
+ 1,
31
+ 1,
32
+ 1,
33
+ 1,
34
+ 1,
35
+ 1,
36
+ 1,
37
+ 1,
38
+ 1,
39
+ 1,
40
+ 1,
41
+ 1,
42
+ 1,
43
+ 1,
44
+ 1,
45
+ 1,
46
+ 1,
47
+ 1,
48
+ 1,
49
+ 1,
50
+ 1,
51
+ 1,
52
+ 1,
53
+ 1,
54
+ 1,
55
+ 1,
56
+ 1,
57
+ 1,
58
+ 1,
59
+ 1,
60
+ 1,
61
+ 1,
62
+ 1,
63
+ 1,
64
+ 1,
65
+ 1,
66
+ 1,
67
+ 1,
68
+ 1
69
+ ],
70
+ "bos_token_id": null,
71
+ "eos_token_id": null,
72
+ "head_dim": 128,
73
+ "hidden_act": "silu",
74
+ "hidden_size": 3072,
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 1536,
77
+ "layernorm_full_attention_beta": 1.0,
78
+ "layernorm_linear_attention_beta": 1.0,
79
+ "layernorm_mlp_beta": 1.0,
80
+ "max_position_embeddings": 196608,
81
+ "mlp_intermediate_size": 8192,
82
+ "model_type": "minimax",
83
+ "mtp_transformer_layers": 1,
84
+ "num_attention_heads": 48,
85
+ "num_experts_per_tok": 8,
86
+ "num_hidden_layers": 62,
87
+ "num_key_value_heads": 8,
88
+ "num_local_experts": 256,
89
+ "num_mtp_modules": 3,
90
+ "output_router_logits": false,
91
+ "qk_norm_type": "per_layer",
92
+ "quantization": {
93
+ "group_size": 64,
94
+ "bits": 3,
95
+ "mode": "affine",
96
+ "model.layers.0.block_sparse_moe.gate": {
97
+ "group_size": 64,
98
+ "bits": 8
99
+ },
100
+ "model.layers.1.block_sparse_moe.gate": {
101
+ "group_size": 64,
102
+ "bits": 8
103
+ },
104
+ "model.layers.2.block_sparse_moe.gate": {
105
+ "group_size": 64,
106
+ "bits": 8
107
+ },
108
+ "model.layers.3.block_sparse_moe.gate": {
109
+ "group_size": 64,
110
+ "bits": 8
111
+ },
112
+ "model.layers.4.block_sparse_moe.gate": {
113
+ "group_size": 64,
114
+ "bits": 8
115
+ },
116
+ "model.layers.5.block_sparse_moe.gate": {
117
+ "group_size": 64,
118
+ "bits": 8
119
+ },
120
+ "model.layers.6.block_sparse_moe.gate": {
121
+ "group_size": 64,
122
+ "bits": 8
123
+ },
124
+ "model.layers.7.block_sparse_moe.gate": {
125
+ "group_size": 64,
126
+ "bits": 8
127
+ },
128
+ "model.layers.8.block_sparse_moe.gate": {
129
+ "group_size": 64,
130
+ "bits": 8
131
+ },
132
+ "model.layers.9.block_sparse_moe.gate": {
133
+ "group_size": 64,
134
+ "bits": 8
135
+ },
136
+ "model.layers.10.block_sparse_moe.gate": {
137
+ "group_size": 64,
138
+ "bits": 8
139
+ },
140
+ "model.layers.11.block_sparse_moe.gate": {
141
+ "group_size": 64,
142
+ "bits": 8
143
+ },
144
+ "model.layers.12.block_sparse_moe.gate": {
145
+ "group_size": 64,
146
+ "bits": 8
147
+ },
148
+ "model.layers.13.block_sparse_moe.gate": {
149
+ "group_size": 64,
150
+ "bits": 8
151
+ },
152
+ "model.layers.14.block_sparse_moe.gate": {
153
+ "group_size": 64,
154
+ "bits": 8
155
+ },
156
+ "model.layers.15.block_sparse_moe.gate": {
157
+ "group_size": 64,
158
+ "bits": 8
159
+ },
160
+ "model.layers.16.block_sparse_moe.gate": {
161
+ "group_size": 64,
162
+ "bits": 8
163
+ },
164
+ "model.layers.17.block_sparse_moe.gate": {
165
+ "group_size": 64,
166
+ "bits": 8
167
+ },
168
+ "model.layers.18.block_sparse_moe.gate": {
169
+ "group_size": 64,
170
+ "bits": 8
171
+ },
172
+ "model.layers.19.block_sparse_moe.gate": {
173
+ "group_size": 64,
174
+ "bits": 8
175
+ },
176
+ "model.layers.20.block_sparse_moe.gate": {
177
+ "group_size": 64,
178
+ "bits": 8
179
+ },
180
+ "model.layers.21.block_sparse_moe.gate": {
181
+ "group_size": 64,
182
+ "bits": 8
183
+ },
184
+ "model.layers.22.block_sparse_moe.gate": {
185
+ "group_size": 64,
186
+ "bits": 8
187
+ },
188
+ "model.layers.23.block_sparse_moe.gate": {
189
+ "group_size": 64,
190
+ "bits": 8
191
+ },
192
+ "model.layers.24.block_sparse_moe.gate": {
193
+ "group_size": 64,
194
+ "bits": 8
195
+ },
196
+ "model.layers.25.block_sparse_moe.gate": {
197
+ "group_size": 64,
198
+ "bits": 8
199
+ },
200
+ "model.layers.26.block_sparse_moe.gate": {
201
+ "group_size": 64,
202
+ "bits": 8
203
+ },
204
+ "model.layers.27.block_sparse_moe.gate": {
205
+ "group_size": 64,
206
+ "bits": 8
207
+ },
208
+ "model.layers.28.block_sparse_moe.gate": {
209
+ "group_size": 64,
210
+ "bits": 8
211
+ },
212
+ "model.layers.29.block_sparse_moe.gate": {
213
+ "group_size": 64,
214
+ "bits": 8
215
+ },
216
+ "model.layers.30.block_sparse_moe.gate": {
217
+ "group_size": 64,
218
+ "bits": 8
219
+ },
220
+ "model.layers.31.block_sparse_moe.gate": {
221
+ "group_size": 64,
222
+ "bits": 8
223
+ },
224
+ "model.layers.32.block_sparse_moe.gate": {
225
+ "group_size": 64,
226
+ "bits": 8
227
+ },
228
+ "model.layers.33.block_sparse_moe.gate": {
229
+ "group_size": 64,
230
+ "bits": 8
231
+ },
232
+ "model.layers.34.block_sparse_moe.gate": {
233
+ "group_size": 64,
234
+ "bits": 8
235
+ },
236
+ "model.layers.35.block_sparse_moe.gate": {
237
+ "group_size": 64,
238
+ "bits": 8
239
+ },
240
+ "model.layers.36.block_sparse_moe.gate": {
241
+ "group_size": 64,
242
+ "bits": 8
243
+ },
244
+ "model.layers.37.block_sparse_moe.gate": {
245
+ "group_size": 64,
246
+ "bits": 8
247
+ },
248
+ "model.layers.38.block_sparse_moe.gate": {
249
+ "group_size": 64,
250
+ "bits": 8
251
+ },
252
+ "model.layers.39.block_sparse_moe.gate": {
253
+ "group_size": 64,
254
+ "bits": 8
255
+ },
256
+ "model.layers.40.block_sparse_moe.gate": {
257
+ "group_size": 64,
258
+ "bits": 8
259
+ },
260
+ "model.layers.41.block_sparse_moe.gate": {
261
+ "group_size": 64,
262
+ "bits": 8
263
+ },
264
+ "model.layers.42.block_sparse_moe.gate": {
265
+ "group_size": 64,
266
+ "bits": 8
267
+ },
268
+ "model.layers.43.block_sparse_moe.gate": {
269
+ "group_size": 64,
270
+ "bits": 8
271
+ },
272
+ "model.layers.44.block_sparse_moe.gate": {
273
+ "group_size": 64,
274
+ "bits": 8
275
+ },
276
+ "model.layers.45.block_sparse_moe.gate": {
277
+ "group_size": 64,
278
+ "bits": 8
279
+ },
280
+ "model.layers.46.block_sparse_moe.gate": {
281
+ "group_size": 64,
282
+ "bits": 8
283
+ },
284
+ "model.layers.47.block_sparse_moe.gate": {
285
+ "group_size": 64,
286
+ "bits": 8
287
+ },
288
+ "model.layers.48.block_sparse_moe.gate": {
289
+ "group_size": 64,
290
+ "bits": 8
291
+ },
292
+ "model.layers.49.block_sparse_moe.gate": {
293
+ "group_size": 64,
294
+ "bits": 8
295
+ },
296
+ "model.layers.50.block_sparse_moe.gate": {
297
+ "group_size": 64,
298
+ "bits": 8
299
+ },
300
+ "model.layers.51.block_sparse_moe.gate": {
301
+ "group_size": 64,
302
+ "bits": 8
303
+ },
304
+ "model.layers.52.block_sparse_moe.gate": {
305
+ "group_size": 64,
306
+ "bits": 8
307
+ },
308
+ "model.layers.53.block_sparse_moe.gate": {
309
+ "group_size": 64,
310
+ "bits": 8
311
+ },
312
+ "model.layers.54.block_sparse_moe.gate": {
313
+ "group_size": 64,
314
+ "bits": 8
315
+ },
316
+ "model.layers.55.block_sparse_moe.gate": {
317
+ "group_size": 64,
318
+ "bits": 8
319
+ },
320
+ "model.layers.56.block_sparse_moe.gate": {
321
+ "group_size": 64,
322
+ "bits": 8
323
+ },
324
+ "model.layers.57.block_sparse_moe.gate": {
325
+ "group_size": 64,
326
+ "bits": 8
327
+ },
328
+ "model.layers.58.block_sparse_moe.gate": {
329
+ "group_size": 64,
330
+ "bits": 8
331
+ },
332
+ "model.layers.59.block_sparse_moe.gate": {
333
+ "group_size": 64,
334
+ "bits": 8
335
+ },
336
+ "model.layers.60.block_sparse_moe.gate": {
337
+ "group_size": 64,
338
+ "bits": 8
339
+ },
340
+ "model.layers.61.block_sparse_moe.gate": {
341
+ "group_size": 64,
342
+ "bits": 8
343
+ }
344
+ },
345
+ "quantization_config": {
346
+ "group_size": 64,
347
+ "bits": 3,
348
+ "mode": "affine",
349
+ "model.layers.0.block_sparse_moe.gate": {
350
+ "group_size": 64,
351
+ "bits": 8
352
+ },
353
+ "model.layers.1.block_sparse_moe.gate": {
354
+ "group_size": 64,
355
+ "bits": 8
356
+ },
357
+ "model.layers.2.block_sparse_moe.gate": {
358
+ "group_size": 64,
359
+ "bits": 8
360
+ },
361
+ "model.layers.3.block_sparse_moe.gate": {
362
+ "group_size": 64,
363
+ "bits": 8
364
+ },
365
+ "model.layers.4.block_sparse_moe.gate": {
366
+ "group_size": 64,
367
+ "bits": 8
368
+ },
369
+ "model.layers.5.block_sparse_moe.gate": {
370
+ "group_size": 64,
371
+ "bits": 8
372
+ },
373
+ "model.layers.6.block_sparse_moe.gate": {
374
+ "group_size": 64,
375
+ "bits": 8
376
+ },
377
+ "model.layers.7.block_sparse_moe.gate": {
378
+ "group_size": 64,
379
+ "bits": 8
380
+ },
381
+ "model.layers.8.block_sparse_moe.gate": {
382
+ "group_size": 64,
383
+ "bits": 8
384
+ },
385
+ "model.layers.9.block_sparse_moe.gate": {
386
+ "group_size": 64,
387
+ "bits": 8
388
+ },
389
+ "model.layers.10.block_sparse_moe.gate": {
390
+ "group_size": 64,
391
+ "bits": 8
392
+ },
393
+ "model.layers.11.block_sparse_moe.gate": {
394
+ "group_size": 64,
395
+ "bits": 8
396
+ },
397
+ "model.layers.12.block_sparse_moe.gate": {
398
+ "group_size": 64,
399
+ "bits": 8
400
+ },
401
+ "model.layers.13.block_sparse_moe.gate": {
402
+ "group_size": 64,
403
+ "bits": 8
404
+ },
405
+ "model.layers.14.block_sparse_moe.gate": {
406
+ "group_size": 64,
407
+ "bits": 8
408
+ },
409
+ "model.layers.15.block_sparse_moe.gate": {
410
+ "group_size": 64,
411
+ "bits": 8
412
+ },
413
+ "model.layers.16.block_sparse_moe.gate": {
414
+ "group_size": 64,
415
+ "bits": 8
416
+ },
417
+ "model.layers.17.block_sparse_moe.gate": {
418
+ "group_size": 64,
419
+ "bits": 8
420
+ },
421
+ "model.layers.18.block_sparse_moe.gate": {
422
+ "group_size": 64,
423
+ "bits": 8
424
+ },
425
+ "model.layers.19.block_sparse_moe.gate": {
426
+ "group_size": 64,
427
+ "bits": 8
428
+ },
429
+ "model.layers.20.block_sparse_moe.gate": {
430
+ "group_size": 64,
431
+ "bits": 8
432
+ },
433
+ "model.layers.21.block_sparse_moe.gate": {
434
+ "group_size": 64,
435
+ "bits": 8
436
+ },
437
+ "model.layers.22.block_sparse_moe.gate": {
438
+ "group_size": 64,
439
+ "bits": 8
440
+ },
441
+ "model.layers.23.block_sparse_moe.gate": {
442
+ "group_size": 64,
443
+ "bits": 8
444
+ },
445
+ "model.layers.24.block_sparse_moe.gate": {
446
+ "group_size": 64,
447
+ "bits": 8
448
+ },
449
+ "model.layers.25.block_sparse_moe.gate": {
450
+ "group_size": 64,
451
+ "bits": 8
452
+ },
453
+ "model.layers.26.block_sparse_moe.gate": {
454
+ "group_size": 64,
455
+ "bits": 8
456
+ },
457
+ "model.layers.27.block_sparse_moe.gate": {
458
+ "group_size": 64,
459
+ "bits": 8
460
+ },
461
+ "model.layers.28.block_sparse_moe.gate": {
462
+ "group_size": 64,
463
+ "bits": 8
464
+ },
465
+ "model.layers.29.block_sparse_moe.gate": {
466
+ "group_size": 64,
467
+ "bits": 8
468
+ },
469
+ "model.layers.30.block_sparse_moe.gate": {
470
+ "group_size": 64,
471
+ "bits": 8
472
+ },
473
+ "model.layers.31.block_sparse_moe.gate": {
474
+ "group_size": 64,
475
+ "bits": 8
476
+ },
477
+ "model.layers.32.block_sparse_moe.gate": {
478
+ "group_size": 64,
479
+ "bits": 8
480
+ },
481
+ "model.layers.33.block_sparse_moe.gate": {
482
+ "group_size": 64,
483
+ "bits": 8
484
+ },
485
+ "model.layers.34.block_sparse_moe.gate": {
486
+ "group_size": 64,
487
+ "bits": 8
488
+ },
489
+ "model.layers.35.block_sparse_moe.gate": {
490
+ "group_size": 64,
491
+ "bits": 8
492
+ },
493
+ "model.layers.36.block_sparse_moe.gate": {
494
+ "group_size": 64,
495
+ "bits": 8
496
+ },
497
+ "model.layers.37.block_sparse_moe.gate": {
498
+ "group_size": 64,
499
+ "bits": 8
500
+ },
501
+ "model.layers.38.block_sparse_moe.gate": {
502
+ "group_size": 64,
503
+ "bits": 8
504
+ },
505
+ "model.layers.39.block_sparse_moe.gate": {
506
+ "group_size": 64,
507
+ "bits": 8
508
+ },
509
+ "model.layers.40.block_sparse_moe.gate": {
510
+ "group_size": 64,
511
+ "bits": 8
512
+ },
513
+ "model.layers.41.block_sparse_moe.gate": {
514
+ "group_size": 64,
515
+ "bits": 8
516
+ },
517
+ "model.layers.42.block_sparse_moe.gate": {
518
+ "group_size": 64,
519
+ "bits": 8
520
+ },
521
+ "model.layers.43.block_sparse_moe.gate": {
522
+ "group_size": 64,
523
+ "bits": 8
524
+ },
525
+ "model.layers.44.block_sparse_moe.gate": {
526
+ "group_size": 64,
527
+ "bits": 8
528
+ },
529
+ "model.layers.45.block_sparse_moe.gate": {
530
+ "group_size": 64,
531
+ "bits": 8
532
+ },
533
+ "model.layers.46.block_sparse_moe.gate": {
534
+ "group_size": 64,
535
+ "bits": 8
536
+ },
537
+ "model.layers.47.block_sparse_moe.gate": {
538
+ "group_size": 64,
539
+ "bits": 8
540
+ },
541
+ "model.layers.48.block_sparse_moe.gate": {
542
+ "group_size": 64,
543
+ "bits": 8
544
+ },
545
+ "model.layers.49.block_sparse_moe.gate": {
546
+ "group_size": 64,
547
+ "bits": 8
548
+ },
549
+ "model.layers.50.block_sparse_moe.gate": {
550
+ "group_size": 64,
551
+ "bits": 8
552
+ },
553
+ "model.layers.51.block_sparse_moe.gate": {
554
+ "group_size": 64,
555
+ "bits": 8
556
+ },
557
+ "model.layers.52.block_sparse_moe.gate": {
558
+ "group_size": 64,
559
+ "bits": 8
560
+ },
561
+ "model.layers.53.block_sparse_moe.gate": {
562
+ "group_size": 64,
563
+ "bits": 8
564
+ },
565
+ "model.layers.54.block_sparse_moe.gate": {
566
+ "group_size": 64,
567
+ "bits": 8
568
+ },
569
+ "model.layers.55.block_sparse_moe.gate": {
570
+ "group_size": 64,
571
+ "bits": 8
572
+ },
573
+ "model.layers.56.block_sparse_moe.gate": {
574
+ "group_size": 64,
575
+ "bits": 8
576
+ },
577
+ "model.layers.57.block_sparse_moe.gate": {
578
+ "group_size": 64,
579
+ "bits": 8
580
+ },
581
+ "model.layers.58.block_sparse_moe.gate": {
582
+ "group_size": 64,
583
+ "bits": 8
584
+ },
585
+ "model.layers.59.block_sparse_moe.gate": {
586
+ "group_size": 64,
587
+ "bits": 8
588
+ },
589
+ "model.layers.60.block_sparse_moe.gate": {
590
+ "group_size": 64,
591
+ "bits": 8
592
+ },
593
+ "model.layers.61.block_sparse_moe.gate": {
594
+ "group_size": 64,
595
+ "bits": 8
596
+ }
597
+ },
598
+ "rms_norm_eps": 1e-06,
599
+ "rope_theta": 5000000,
600
+ "rotary_dim": 64,
601
+ "router_aux_loss_coef": 0.001,
602
+ "router_jitter_noise": 0.0,
603
+ "scoring_func": "sigmoid",
604
+ "shared_intermediate_size": 0,
605
+ "shared_moe_mode": "sigmoid",
606
+ "sliding_window": null,
607
+ "tie_word_embeddings": false,
608
+ "transformers_version": "4.46.1",
609
+ "use_cache": true,
610
+ "use_mtp": true,
611
+ "use_qk_norm": true,
612
+ "use_routing_bias": true,
613
+ "vocab_size": 200064
614
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "temperature": 1.0,
4
+ "top_p": 0.95,
5
+ "top_k": 40,
6
+ "transformers_version": "4.46.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0583b966f8d771579f246d50d355e991d2614a6d5e5dad11abc0162cfee508c5
3
+ size 5105946242
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfb95c086e26b3bc601e8c0c1a484531e971f9cf70e8ef07d0c9ee3522b35f9
3
+ size 5345374071
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11c6734473a312348a8705fc86609c55bb016c5b5308c66df1bf4931090da1d
3
+ size 5345374063
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:860930309828068043b208a28b7833748891646b4adca50262c7bb07cd8ea5d7
3
+ size 5365556366
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:284ab29393a8a7b6169ed6e61957a99b7816475d4d2cf2d1db64acfa24dc9076
3
+ size 5345374165
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc172737fdc5bfaa9428a3e0268e0bed65cf902586c6272307c909c2504d0085
3
+ size 5345374093
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbec5c76e630873edc7a9c8cae83ce53d195dd0471f093ceb7834891cea8a2da
3
+ size 5365556384
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dd5961fdd73800f23f434a04671d6459db669dfbfb9e2f648d3c7760db2cbe
3
+ size 5345374163
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf99535f214fbb2ec6960589a8b8d27d60e0eac6d5c37686cf5b4c51a4d6a32
3
+ size 5345374113
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c21593ed8c8f709982af22b02dbf26270cc2ef781988d519545adbe7224af92
3
+ size 5365556348
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3698a03f7e88662d49e7020e197b25517215b149185366324e55a493ae20b4a
3
+ size 5345374163
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee590bb71308044614a143dd791e3fe8e4e9ab7e82d258027c749b14d34b5df
3
+ size 5345374169
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2480c5232f4df3b9eac4e21aac965c8bf29308bf253cf7cd5a9ca6913e7a03d3
3
+ size 5365556434
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb50287bd4e723fb3afb9461d478de670fea0cdb3bff39e6e5fbc41f76791b9
3
+ size 5345374087
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b405c6eb0bc2e48763105ba7cb2961ac9a20357e9527878dd1ed28c365762e88
3
+ size 5345374153
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffab19e0ab8955f937ddca937595800f1f56f29d57cbbe2715031b59f0db0b2d
3
+ size 5365556386
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a887b624d1191f7c5c9cbaca531f030453603e500575fe22207be94c66ba778
3
+ size 5345374169
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d46d8a51ec6e0478794d10b10b4a1478abfbfb9f34dc574cc2d540208a64fa
3
+ size 5345374163
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d04d89cfb7263bd33145c366c0f26aa90c201f93e03e940db297b9f616a109
3
+ size 4008649866
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<code_interpreter>",
4
+ "<commit_after>",
5
+ "<commit_before>",
6
+ "<commit_msg>",
7
+ "<empty_output>",
8
+ "<filename>",
9
+ "<fim_middle>",
10
+ "<fim_pad>",
11
+ "<fim_prefix>",
12
+ "<fim_suffix>",
13
+ "<function_call>",
14
+ "<gh_stars>",
15
+ "]<]speech[>[",
16
+ "]<]image[>[",
17
+ "]<]video[>[",
18
+ "]<]start of speech[>[",
19
+ "]<]end of speech[>[",
20
+ "]<]start of image[>[",
21
+ "]<]end of image[>[",
22
+ "]<]start of video[>[",
23
+ "]<]end of video[>[",
24
+ "]<]vision pad[>[",
25
+ "]~!b[",
26
+ "<issue_closed>",
27
+ "<issue_comment>",
28
+ "<issue_start>",
29
+ "<jupyter_code>",
30
+ "<jupyter_output>",
31
+ "<jupyter_start>",
32
+ "<jupyter_text>",
33
+ "<reponame>",
34
+ "[e~[",
35
+ "]!d~[",
36
+ "]!p~[",
37
+ "]~b]",
38
+ "<jupyter_error>",
39
+ "<add_file>",
40
+ "<delete_file>",
41
+ "<rename_file>",
42
+ "<edit_file>",
43
+ "<commit_message>",
44
+ "<empty_source_file>",
45
+ "<repo_struct>",
46
+ "<code_context>",
47
+ "<file_content>",
48
+ "<source_files>",
49
+ "<pr_start>",
50
+ "<review_comment>",
51
+ "<filepath>",
52
+ "<file_sep>"
53
+ ],
54
+ "bos_token": {
55
+ "content": "]~!b[",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ },
61
+ "eos_token": {
62
+ "content": "[e~[",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "unk_token": {
69
+ "content": "]!d~[",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ }
75
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b90ed7f55d905175bc26771d6d7d33b40b46742f073675bc816fedaf482ea1
3
+ size 15522763
tokenizer_config.json ADDED
@@ -0,0 +1,496 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "200000": {
5
+ "content": "]!p~[",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "200001": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "200002": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "200003": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "200004": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "200005": {
45
+ "content": "<reponame>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "200006": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "200007": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "200008": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "200009": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "200010": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "200011": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "200012": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "200013": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "200014": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "200015": {
125
+ "content": "<empty_output>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "200016": {
133
+ "content": "<commit_before>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "200017": {
141
+ "content": "<commit_msg>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "200018": {
149
+ "content": "<commit_after>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "200019": {
157
+ "content": "]~b]",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "200020": {
165
+ "content": "[e~[",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "200021": {
173
+ "content": "]!d~[",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "200022": {
181
+ "content": "<function_call>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "200023": {
189
+ "content": "<code_interpreter>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "200024": {
197
+ "content": "]<]speech[>[",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "200025": {
205
+ "content": "]<]image[>[",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "200026": {
213
+ "content": "]<]video[>[",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "200027": {
221
+ "content": "]<]start of speech[>[",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "200028": {
229
+ "content": "]<]end of speech[>[",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "200029": {
237
+ "content": "]<]start of image[>[",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "200030": {
245
+ "content": "]<]end of image[>[",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "200031": {
253
+ "content": "]<]start of video[>[",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "200032": {
261
+ "content": "]<]end of video[>[",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "200033": {
269
+ "content": "]<]vision pad[>[",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "200034": {
277
+ "content": "]~!b[",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "200035": {
285
+ "content": "<jupyter_error>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "200036": {
293
+ "content": "<add_file>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "200037": {
301
+ "content": "<delete_file>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "200038": {
309
+ "content": "<rename_file>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "200039": {
317
+ "content": "<edit_file>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "200040": {
325
+ "content": "<commit_message>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "200041": {
333
+ "content": "<empty_source_file>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "200042": {
341
+ "content": "<repo_struct>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "200043": {
349
+ "content": "<code_context>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "200044": {
357
+ "content": "<file_content>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "200045": {
365
+ "content": "<source_files>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "200046": {
373
+ "content": "<pr_start>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "200047": {
381
+ "content": "<review_comment>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "200048": {
389
+ "content": "<filepath>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "200049": {
397
+ "content": "<file_sep>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "200050": {
405
+ "content": "<think>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "200051": {
413
+ "content": "</think>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "200052": {
421
+ "content": "<minimax:tool_call>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "200053": {
429
+ "content": "</minimax:tool_call>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ }
436
+ },
437
+ "additional_special_tokens": [
438
+ "<code_interpreter>",
439
+ "<commit_after>",
440
+ "<commit_before>",
441
+ "<commit_msg>",
442
+ "<empty_output>",
443
+ "<filename>",
444
+ "<fim_middle>",
445
+ "<fim_pad>",
446
+ "<fim_prefix>",
447
+ "<fim_suffix>",
448
+ "<function_call>",
449
+ "<gh_stars>",
450
+ "]<]speech[>[",
451
+ "]<]image[>[",
452
+ "]<]video[>[",
453
+ "]<]start of speech[>[",
454
+ "]<]end of speech[>[",
455
+ "]<]start of image[>[",
456
+ "]<]end of image[>[",
457
+ "]<]start of video[>[",
458
+ "]<]end of video[>[",
459
+ "]<]vision pad[>[",
460
+ "]~!b[",
461
+ "<issue_closed>",
462
+ "<issue_comment>",
463
+ "<issue_start>",
464
+ "<jupyter_code>",
465
+ "<jupyter_output>",
466
+ "<jupyter_start>",
467
+ "<jupyter_text>",
468
+ "<reponame>",
469
+ "[e~[",
470
+ "]!d~[",
471
+ "]!p~[",
472
+ "]~b]",
473
+ "<jupyter_error>",
474
+ "<add_file>",
475
+ "<delete_file>",
476
+ "<rename_file>",
477
+ "<edit_file>",
478
+ "<commit_message>",
479
+ "<empty_source_file>",
480
+ "<repo_struct>",
481
+ "<code_context>",
482
+ "<file_content>",
483
+ "<source_files>",
484
+ "<pr_start>",
485
+ "<review_comment>",
486
+ "<filepath>",
487
+ "<file_sep>"
488
+ ],
489
+ "bos_token": "]~!b[",
490
+ "clean_up_tokenization_spaces": false,
491
+ "eos_token": "[e~[",
492
+ "extra_special_tokens": {},
493
+ "model_max_length": 40960000,
494
+ "tokenizer_class": "GPT2Tokenizer",
495
+ "unk_token": "]!d~["
496
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff