Giter Club home page Giter Club logo

mindchat's Issues

gradio版本是不是有问题呀

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'

gguf模型提供下载吗

Feb 20, 2024: 提供MindChat-Qwen2-0_5B、MindChat-Qwen2-4B、MindChat-Qwen2-7B、MindChat-Qwen2-14B对应的gguf模型。

在qwen里运行webdemo报错了

(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'

关于数据集的疑问

感谢作者提供的心理学大模型,其中有一点小疑问,还望赐教
关于数据集示例:data/dataset_example.json
其中部分数据output为空比如:

  {
    "instruction": "非常感谢您的帮助和理解,我期待着与您共同开启这段治疗之旅,为自己的成长和心理健康而努力。",
    "input": "通过指导,我相信您可以逐渐建立起更清晰、更积极的自我认知,降低对他人评价的过度依赖,并且培养更强大的内在自信。",
    "output": "",
    "history": [
      ["我太过在乎别人看法", "是在乎一些重要人的看法呢?还是对于每个人的看法都很在乎呢?"],
      ["我对所有人的看法都很在乎,我害怕被别人拒绝或批评,觉得自己不配和别人交往。", "你对他人看法的在乎和害怕被拒绝或批评,以及对自己价值的质疑,可能表现为社交焦虑和自尊问题。"],
      ["我不会打招呼,不敢面对现实。", "我理解你目前感到的困扰和不安。面对社交和现实中的挑战可能会让我们感到不自信和害怕。但请记住,每个人都有自己的不足和紧张时刻,这是正常的。"],
      ["我不知道要怎么改变这一现状", "在乎别人看法,是不确定自己是怎样的,对自己没有清晰的认识。可以通过咨询客观的认识自己。"]
    ]
  },

请问这么设计的原因是什么呢?

评估参考

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?
image
期待您的回复!

希望获得联系

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。

请问训练MindChat-Qwen-7B-v2模型,训练数据做了预处理了吗

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?

关于微调

看了下直播回放,内容还是在讲纯技术实现,即类似lora的原理;请问是否可以在readme放出微调应用示例呢?或是给个参考之类的

希望取得联系

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

多轮对话

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!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.