Add library name, pipeline tag
Browse filesThis PR makes sure the model can be found at https://huggingface.co/models?pipeline_tag=text-generation as well as adding the `library_name`.
README.md
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
---
|
2 |
# For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
|
3 |
# Doc / guide: https://huggingface.co/docs/hub/datasets-cards
|
4 |
-
|
|
|
|
|
5 |
---
|
6 |
|
7 |
# CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
|
@@ -70,4 +72,212 @@ If you find these resources helpful, please kindly cite as:
|
|
70 |
journal={arXiv preprint arXiv:2502.07316},
|
71 |
year={2025}
|
72 |
}
|
73 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
# For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
|
3 |
# Doc / guide: https://huggingface.co/docs/hub/datasets-cards
|
4 |
+
library_name: transformers
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
---
|
7 |
---
|
8 |
|
9 |
# CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
|
|
|
72 |
journal={arXiv preprint arXiv:2502.07316},
|
73 |
year={2025}
|
74 |
}
|
75 |
+
```
|
76 |
+
|
77 |
+
# File information
|
78 |
+
|
79 |
+
The repository contains the following file information:
|
80 |
+
|
81 |
+
Filename: tokenizer_config.json
|
82 |
+
Content: {
|
83 |
+
"add_bos_token": true,
|
84 |
+
"add_eos_token": false,
|
85 |
+
"bos_token": {
|
86 |
+
"__type": "AddedToken",
|
87 |
+
"content": "<\uff5cbegin\u2581of\u2581sentence\uff5c>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false
|
92 |
+
},
|
93 |
+
"clean_up_tokenization_spaces": false,
|
94 |
+
"eos_token": {
|
95 |
+
"__type": "AddedToken",
|
96 |
+
"content": "<\uff5cend\u2581of\u2581sentence\uff5c>",
|
97 |
+
"lstrip": false,
|
98 |
+
"normalized": true,
|
99 |
+
"rstrip": false,
|
100 |
+
"single_word": false
|
101 |
+
},
|
102 |
+
"legacy": true,
|
103 |
+
"model_max_length": 16384,
|
104 |
+
"pad_token": {
|
105 |
+
"__type": "AddedToken",
|
106 |
+
"content": "<\uff5cend\u2581of\u2581sentence\uff5c>",
|
107 |
+
"lstrip": false,
|
108 |
+
"normalized": true,
|
109 |
+
"rstrip": false,
|
110 |
+
"single_word": false
|
111 |
+
},
|
112 |
+
"sp_model_kwargs": {},
|
113 |
+
"unk_token": null,
|
114 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
115 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<\uff5cUser\uff5c>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<\uff5cAssistant\uff5c><\uff5ctool\u2581calls\u2581begin\uff5c><\uff5ctool\u2581call\u2581begin\uff5c>' + tool['type'] + '<\uff5ctool\u2581sep\uff5c>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<\uff5ctool\u2581call\u2581end\uff5c>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<\uff5ctool\u2581call\u2581begin\uff5c>' + tool['type'] + '<\uff5ctool\u2581sep\uff5c>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<\uff5ctool\u2581call\u2581end\uff5c>'}}{{'<\uff5ctool\u2581calls\u2581end\uff5c><\uff5cend\u2581of\u2581sentence\uff5c>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<\uff5ctool\u2581outputs\u2581end\uff5c>' + message['content'] + '<\uff5cend\u2581of\u2581sentence\uff5c>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<\uff5cAssistant\uff5c>' + content + '<\uff5cend\u2581of\u2581sentence\uff5c>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<\uff5ctool\u2581outputs\u2581begin\uff5c><\uff5ctool\u2581output\u2581begin\uff5c>' + message['content'] + '<\uff5ctool\u2581output\u2581end\uff5c>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<\uff5ctool\u2581output\u2581begin\uff5c>' + message['content'] + '<\uff5ctool\u2581output\u2581end\uff5c>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<\uff5ctool\u2581outputs\u2581end\uff5c>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<\uff5cAssistant\uff5c>'}}{% endif %}"
|
116 |
+
}
|
117 |
+
|
118 |
+
Filename: generation_config.json
|
119 |
+
Content: {
|
120 |
+
"_from_model_config": true,
|
121 |
+
"bos_token_id": 32000,
|
122 |
+
"eos_token_id": 32001,
|
123 |
+
"transformers_version": "4.34.1"
|
124 |
+
}
|
125 |
+
|
126 |
+
Filename: config.json
|
127 |
+
Content: {
|
128 |
+
"architectures": [
|
129 |
+
"LlamaForCausalLM"
|
130 |
+
],
|
131 |
+
"bos_token_id": 32000,
|
132 |
+
"eos_token_id": 32001,
|
133 |
+
"hidden_act": "silu",
|
134 |
+
"hidden_size": 4096,
|
135 |
+
"initializer_range": 0.02,
|
136 |
+
"intermediate_size": 14336,
|
137 |
+
"max_position_embeddings": 32768,
|
138 |
+
"model_type": "llama",
|
139 |
+
"num_attention_heads": 32,
|
140 |
+
"num_hidden_layers": 32,
|
141 |
+
"num_key_value_heads": 8,
|
142 |
+
"pretraining_tp": 1,
|
143 |
+
"rms_norm_eps": 1e-06,
|
144 |
+
"rope_scaling": null,
|
145 |
+
"rope_theta": 100000,
|
146 |
+
"tie_word_embeddings": false,
|
147 |
+
"torch_dtype": "bfloat16",
|
148 |
+
"transformers_version": "4.34.1",
|
149 |
+
"use_cache": true,
|
150 |
+
"vocab_size": 32256
|
151 |
+
}
|
152 |
+
|
153 |
+
Filename: tokenizer.json
|
154 |
+
Content: "Content of the file is larger than 50 KB, too long to display."
|
155 |
+
|
156 |
+
Filename: model.safetensors.index.json
|
157 |
+
Content: {
|
158 |
+
"metadata": {
|
159 |
+
"total_size": 16060522496
|
160 |
+
},
|
161 |
+
"weight_map": {
|
162 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
163 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
194 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
195 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
199 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
200 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
202 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
203 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
204 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
206 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
208 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
209 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
210 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
211 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
212 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
213 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
214 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
215 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
216 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
217 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
218 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
219 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
220 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
221 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
222 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
223 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
224 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
225 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
226 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
227 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
228 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
229 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
230 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
231 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
232 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
233 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
234 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
235 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
236 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
237 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
238 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
239 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
240 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
241 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
242 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
243 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
244 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
245 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
246 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
247 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
248 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
249 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
250 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
251 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
252 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
253 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
254 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
255 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
256 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
257 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
258 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
259 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
260 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
261 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
262 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
263 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
264 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
265 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
266 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
267 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
268 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
269 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
270 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
271 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
272 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors",
|
273 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
|
274 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
|
275 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
|
276 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
|
277 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
|
278 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
|
279 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
|
280 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
|
281 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors",
|
282 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
|
283 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
|