fix chat template Exaone3.0

This commit is contained in:
shing100 2024-09-30 09:44:21 +09:00
parent 0dfe9f763b
commit 2964b20eb5
3 changed files with 0 additions and 4 deletions

View File

@ -169,7 +169,6 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Exaone3.0](https://huggingface.co/LGAI-EXAONE) | 7.8B | exaone |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |

View File

@ -170,7 +170,6 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Exaone3.0](https://huggingface.co/LGAI-EXAONE) | 7.8B | exaone |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |

View File

@ -648,10 +648,8 @@ _register_template(
name="exaone",
format_user=StringFormatter(slots=["[|user|]{{content}}\n[|assistant|]"]),
format_system=StringFormatter(slots=["[|system|]{{content}}[|endofturn|]\n"]),
format_assistant=StringFormatter(slots=["{{content}}[|endofturn|]\n"]),
format_separator=EmptyFormatter(slots=["\n"]),
format_prefix=EmptyFormatter(slots=[""]),
stop_words=["[|endofturn|]"],
efficient_eos=True,
)