bakaEC/OliveSensorAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

webV3 opt (#280)

Browse Source
This commit is contained in:
HongCheng 2024-07-17 15:26:34 +09:00 committed by GitHub
commit 456e3de78a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -46,7 +46,7 @@
| 模型 | 类型 | 链接 | 模型链接 | | 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_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 | 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) | | 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) |

2
README_EN.md
View File

@ -48,7 +48,7 @@
| Model | Type | File Links | Model Links | | 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_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 | 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) | | 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) |

4
web_internlm2_5.py
View File

@ -223,7 +223,7 @@ cur_query_prompt = '<|im_start|>user\n{user}<|im_end|>\n\
def combine_history(prompt): def combine_history(prompt):
messages = st.session_state.messages 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' total_prompt = f'<s><|im_start|>system\n{meta_instruction}<|im_end|>\n'
for message in messages: for message in messages:
cur_content = message['content'] cur_content = message['content']
@ -239,7 +239,7 @@ def combine_history(prompt):
def main(): 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() # torch.cuda.empty_cache()
print('load model begin.') print('load model begin.')
model, tokenizer = load_model() model, tokenizer = load_model()