x-d-lab / mindchat Goto Github PK

作者：
你们好，非常感谢你们这项工作对心理大模型开源社区的贡献。
想请问模型训练完之后，如何进行训练效果的评估？
另外想请问下，readme下面这张图里面的评估的对象是与模型正在聊天的人吗？

期待您的回复！

尊敬的MindChat 应用开发者，我是 InternLM 社区开发者&志愿者尖米, 大佬开源的工作对我的启发很大，希望可以探讨使用 InternLM 实现MindChat 的可能性和实现路径，我的微信是mzm312，希望可以取得联系进行更深度的交流

大佬们什么时候有开源计划？

大佬您好！我也想微调个这种心理咨询的聊天模型，想请教下您的对话数据是怎么来的？
非常感谢！

ab/flash-attention
Loading checkpoint shards: 100%|████████████████████████████████████████████████████| 8/8 [00:12<00:00, 1.61s/it]
Traceback (most recent call last):
File "/data/code/MindChat/webui_demo.py", line 58, in
demo = gr.ChatInterface(predict,
File "/data/jt_conda/mindchat/lib/python3.9/site-packages/gradio/chat_interface.py", line 273, in init
client_utils.synchronize_async(self.examples_handler.cache)
AttributeError: 'ChatInterface' object has no attribute 'examples_handler'

大佬们，什么时候可以先搞个 openai_api文件 就可以接接口了呀

(my-env) root@autodl-container-072d119c3c-81e484cb:~/autodl-tmp/Qwen# python web_demo.py
Warning: import flash_attn rms_norm fail, please install FlashAttention layer_norm to get better performance https://github.com/Dao-AILab/flash-attention/tree/main/csrc/layer_norm
Warning: import flash_attn fail, please install FlashAttention https://github.com/Dao-AILab/flash-attention
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:16<00:00, 8.21s/it]
WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu.
Running on local URL: http://127.0.0.1:6006

To create a public link, set share=True in launch().
User: nihao
Traceback (most recent call last):
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/blocks.py", line 1431, in process_api
result = await self.call_function(
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/blocks.py", line 1117, in call_function
prediction = await utils.async_iteration(iterator)
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/utils.py", line 350, in async_iteration
return await iterator.anext()
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/utils.py", line 343, in anext
return await anyio.to_thread.run_sync(
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
result = context.run(func, *args)
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/utils.py", line 326, in run_sync_iterator_async
return next(iterator)
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/gradio/utils.py", line 695, in gen_wrapper
yield from f(*args, **kwargs)
File "/root/autodl-tmp/Qwen/web_demo.py", line 124, in predict
for response in model.chat_stream(tokenizer, _query, history=_task_history, generation_config=config):
File "/root/miniconda3/envs/my-env/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'QWenLMHeadModel' object has no attribute 'chat_stream'

MindChat-Qwen-7B-v2 的模型是基于qwen-7b 吗？我看qwen-7b 训练前会把数据预处理成下边格式：
<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n
<|im_start|>user\n你好<|im_end|>\n
<|im_start|>assistant\n你好！很高兴为你提供帮助。<|im_end|>\n
<|im_start|>user\n给我讲一个年轻人奋斗创业最终取得成功的故事。<|im_end|>\n
<|im_start|>assistant\n
请问咱们会对数据也做一样处理吗？
我看提供的推理代码也没有做数据前处理。https://github.com/X-D-Lab/MindChat/tree/main/scripts
所以我想确认下最终咱们训练数据是做成什么格式？

报错是
AttributeError: 'BaichuanTokenizer' object has no attribute 'sp_model'

rt

希望能提供个接口调用，谢谢

我是 InternLM 的社区开发者，看到您的项目觉得非常不错，希望能够加您的微信，我的微信号是mzm312，我们希望您的项目能够部署到社区，我们将提供算力部署。

项目readme貌似只有相关介绍，并未提供模型使用方式？