Dev2Main EmoLLMV3 (#281)

2024-07-17 15:32:58 +09:00 · 2024-07-17 15:32:58 +09:00 · 93439fc52a
commit 93439fc52a
parent 5ff357fb77 05faabeef7
3 changed files with 6 additions and 6 deletions
--- a/README.md
+++ b/README.md
@ -46,7 +46,7 @@

 |         模型          |   类型   |                                                   链接                                                   | 模型链接   |
 | :-------------------: | :------: | :------------------------------------------------------------------------------------------------------: |:------: |
-|   InternLM2_5_7B_chat   |  全量微调   |  [internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py) | [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) |
+|   InternLM2_5_7B_chat   |  全量微调   |  [internlm2_5_chat_7b_full.py](./xtuner_config/internlm2_5_chat_7b_full.py) | [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) |
 |   InternLM2_5_7B_chat   |  QLORA   |  [internlm2_5_chat_7b_qlora_oasst1_e3.py](./xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py) |[ModelScope](https://www.modelscope.cn/models/z342994309/emollm_interlm2_5/)  |
 |   InternLM2_7B_chat   |  QLORA   |  [internlm2_7b_chat_qlora_e3.py](./xtuner_config/internlm2_7b_chat_qlora_e3.py) | [ModelScope](https://modelscope.cn/models/aJupyter/EmoLLM/files) |
 |   InternLM2_7B_chat   | 全量微调 | [internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py)  | [OpenXLab](https://openxlab.org.cn/models/detail/ajupyter/EmoLLM_internlm2_7b_full) |
@ -100,7 +100,7 @@
 </table>

 ## 🎇最近更新
- 【2024.07.16】欢迎大家体验 EmoLLM V3.0 ，改模型是基于InternLM2.5-7B-Chat模型的全量微调，微调配置文件地址：[internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py) ，模型权重链接：[OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) ，WebDemo地址： [OpenXLab apps](https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0), [配套全量微调知乎教程](https://zhuanlan.zhihu.com/p/708931911)。
+- 【2024.07.16】欢迎大家体验 EmoLLM V3.0 ，该模型是基于InternLM2.5-7B-Chat模型的全量微调，微调配置文件地址：[internlm2_5_chat_7b_full.py](./xtuner_config/internlm2_5_chat_7b_full.py) ，模型权重链接：[OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) ，WebDemo地址： [OpenXLab apps](https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0), [配套全量微调知乎教程](https://zhuanlan.zhihu.com/p/708931911)。
 - 【2024.07】欢迎大家使用稳定版 EmoLLM V2.0 进行日常使用和学术研究，模型权重链接：[OpenXLab](https://openxlab.org.cn/models/detail/ajupyter/EmoLLM_internlm2_7b_full/tree/main)。
 - 【2024.07】新增基于InternLM2_5_7B_chat[微调配置](./xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py)、模型文件发布在 [ModelScope](https://www.modelscope.cn/models/z342994309/emollm_interlm2_5/)。
 - 【2024.06】新增基于[LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)[GLM4-9B-chat微调指南](./doc/GLM-4-9B-chat%20Lora%20微调（llama-factory）.md)、新增[基于swift的微调指南](./swift/)、论文[ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models](https://arxiv.org/abs/2406.14952)引用了EmoLLM且EmoLLM取得了较好的效果。
--- a/README_EN.md
+++ b/README_EN.md
@ -48,7 +48,7 @@

 |         Model         |       Type       | File Links  | Model Links  |
 | :-------------------: | :------: | :------------------------------------------------------------------------------------------------------: |:------: |
-|   InternLM2_5_7B_chat   |  全量微调   |  [internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py) | [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) |
+| InternLM2_5_7B_chat | full fine-tuing | [internlm2_5_chat_7b_full.py](./xtuner_config/internlm2_5_chat_7b_full.py)| [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0) |
 |   InternLM2_5_7B_chat   |  QLORA   |  [internlm2_5_chat_7b_qlora_oasst1_e3.py](./xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py) |[ModelScope](https://www.modelscope.cn/models/z342994309/emollm_interlm2_5/)  |
 |   InternLM2_7B_chat   |  QLORA   |  [internlm2_7b_chat_qlora_e3.py](./xtuner_config/internlm2_7b_chat_qlora_e3.py) | [ModelScope](https://modelscope.cn/models/aJupyter/EmoLLM/files) |
 |   InternLM2_7B_chat   | full fine-tuing | [internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py)  | [OpenXLab](https://openxlab.org.cn/models/detail/ajupyter/EmoLLM_internlm2_7b_full) |
@ -104,7 +104,7 @@ The Model aims to fully understand and promote the mental health of individuals,
 </table>

 ## Recent Updates
- 【2024.07.16】 Welcome everyone to experience EmoLLM V3.0. This model is a fully fine-tuned version based on the InternLM2.5-7B-Chat model. The fine-tuning configuration file can be found at: [internlm2_chat_7b_full.py](./xtuner_config/internlm2_chat_7b_full.py). Model weights are available at: [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0). WebDemo is available at: [OpenXLab apps](https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0), [Full fine-tuning tutorial on Zhihu](https://zhuanlan.zhihu.com/p/708931911).
+- 【2024.07.16】 Welcome everyone to experience EmoLLM V3.0. This model is a fully fine-tuned version based on the InternLM2.5-7B-Chat model. The fine-tuning configuration file can be found at: [internlm2_5_chat_7b_full.py](./xtuner_config/internlm2_5_chat_7b_full.py). Model weights are available at: [OpenXLab](https://openxlab.org.cn/models/detail/chg0901/EmoLLM_V3.0), [ModelScope](https://modelscope.cn/models/chg0901/EmoLLMV3.0). WebDemo is available at: [OpenXLab apps](https://openxlab.org.cn/apps/detail/chg0901/EmoLLMV3.0), [Full fine-tuning tutorial on Zhihu](https://zhuanlan.zhihu.com/p/708931911).
 - 【2024.07】Welcome to use the stable version of EmoLLM V2.0 for daily use and academic research. Model weight link: [OpenXLab](https://openxlab.org.cn/models/detail/ajupyter/EmoLLM_internlm2_7b_full/tree/main).
 - 【2024.07】Added InternLM2_5_7B_chat[fine-tuning configuration](./xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py)、model file [ModelScope](https://www.modelscope.cn/models/z342994309/emollm_interlm2_5/)。
 - 【2024.06】 Added [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)[GLM4-9B-chat fine-tuning guide](./doc/GLM-4-9B-chat%20Lora%20微调（llama-factory）.md), added [swift-based fine-tuning guide](./swift/), the paper [ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models](https://arxiv.org/abs/2406.14952) cited EmoLLM and EmoLLM achieved good results.
--- a/web_internlm2_5.py
+++ b/web_internlm2_5.py
@ -223,7 +223,7 @@ cur_query_prompt = '<|im_start|>user\n{user}<|im_end|>\n\

 def combine_history(prompt):
    messages = st.session_state.messages
-    meta_instruction = ('你是EmoLLM心理咨询师, 由EmoLLM团队打造, 是一个研究过无数具有心理咨询者与顶级专业心理咨询师对话的心理学教授, 在心理方面拥有广博的知识储备和丰富的研究咨询经验。你旨在通过专业心理咨询, 协助来访者完成心理诊断, 利用专业心理学知识与咨询技术一步步帮助来访者解决心理问题。')
+    meta_instruction = ('你是EmoLLM心理咨询师, 由EmoLLM团队打造, 是一个研究过无数具有心理咨询者与顶级专业心理咨询师对话的心理学教授, 在心理方面拥有广博的知识储备和丰富的研究咨询经验。你旨在通过专业心理咨询, 协助来访者完成心理诊断, 利用专业心理学知识与咨询技术一步步帮助来访者解决心理问题。如果有必要，请用“咨询者”称呼对话咨询的用户。')
    total_prompt = f'<s><|im_start|>system\n{meta_instruction}<|im_end|>\n'
    for message in messages:
        cur_content = message['content']
@ -239,7 +239,7 @@ def combine_history(prompt):


 def main():
-    st.markdown("我在这里，准备好倾听你的心声了。", unsafe_allow_html=True)
+    # st.markdown("我在这里，准备好倾听你的心声了。", unsafe_allow_html=True)
    # torch.cuda.empty_cache()
    print('load model begin.')
    model, tokenizer = load_model()