在多轮对话infei时会出现大量的#号，这是为什么

: 小张最近感觉身体不适，出现心悸、气促等症状。体检发现心脏扩大、搏动减弱。 : 我建议您及家人及您的医生进行进一步的检查，以确定小张的病因。同时，我建让您及家人做好的饮食和生活习惯，以避免其他的健康问题。###########################################################################################################################: 小王被确诊为肝炎双重感染，最可能的并发症是什么？ : 根据相关文献，肝炎双重感染的危险因素主要包括肝炎、营养不良、免疫抑制剂、病毒敏感免疫等。因此，我建让您及家人及您的医生进行进一步的检查，以确定小张的病因。

能否将LoRA都传一份到Huggingface上，百度网盘出现奇妙bug

看到你们的项目中利用GPT3.5接口围绕医学文献多轮问答数据，我觉得这个idea很好。但是从示意图当中还是没太看明白具体是怎样生成多轮问答数据的。能再给出具体的解释吗？多谢！

def main(
load_8bit: bool = True,
base_model: str = "decapoda-research/llama-7b-hf",
# the infer data, if not exists, infer the default instructions in code
instruct_dir: str = "./data/infer.json",
use_lora: bool = True,
lora_weights: str = "tloen/alpaca-lora-7b",
# The prompt template to use, will default to med_template.
prompt_template: str = "med_template",
):我的配置参数是这样的，其他的都和初始的一样，但我运行之后报错
│ │
│ /usr/local/lib/python3.9/dist-packages/bitsandbytes/autograd/_functions.py:3 │
│ 80 in forward │
│ │
│ 377 │ │ │ if state.CxB is not None: │
│ 378 │ │ │ │ outliers = F.extract_outliers(state.CxB, state.SB, sta │
│ 379 │ │ │ else: │
│ ❱ 380 │ │ │ │ outliers = state.CB[:, state.idx.long()].clone() │
│ 381 │ │ │ │
│ 382 │ │ │ state.subB = (outliers * state.SCB.view(-1, 1) / 127.0).t( │
│ 383 │ │ │ CA[:, state.idx.long()] = 0 │
╰──────────────────────────────────────────────────────────────────────────────╯
TypeError: 'NoneType' object is not subscriptable

Process finished with exit code 1
我不知道为什么会这样，有人可以给我指导一下吗

使用lora-alpaca-med进行推理的时候，prompt_template应该选择什么呢, med-template.json还是alpaca_short.json？

如题。

Hello！
想问下是否有用到其他数据集（除了instruct生成的数据外）？

是效果不好还是什么原因？

在本地测了Chinese-alpaca-7b + lora-alpaca-med-alldata，在多轮对话上，效果很好。

请问：

1. 如何利用llama.json以及liver_cancer.json，如何合并数据集（一个多轮对话，一个单轮对话），直接合并放在一个文件么？
2. 复现您们的训练效果，该使用哪个模板？('med_template' or 'literature_template.json')
3. 目前我有 8 X A100(40G)， micro_batch_size和batch_size该如何设置（都是64么？为您们设置的一半？）
4. 关于LoRA的rank和alpha值？听说在垂直领域微调时，加大LoRA的rank值效果会好些，想问下您们关于LoRA的rank值以及alpha值的选取的相关经验

感谢您们百忙之中抽空解答，祝项目越来越好，感谢！

/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/usr/local/cuda/lib64/libcudart.so.11.0'), PosixPath('/usr/local/cuda/lib64/libcudart.so')}.. We'll flip a coin and try one of these, in order to fail forward.
Either way, this might cause trouble in the future:
If you get CUDA error: invalid device function errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.
warn(msg)
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so.11.0
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 114
CUDA SETUP: Loading binary /home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/bitsandbytes/libbitsandbytes_cuda114.so...
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'LLaMATokenizer'.
The class this function is called from is 'LlamaTokenizer'.
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:14<00:00, 2.29it/s]
using lora ./lora-llama-med
Traceback (most recent call last):
File "/mnt/datadisk0/code/Huatuo-Llama-Med-Chinese/infer.py", line 125, in
fire.Fire(main)
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/fire/core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/mnt/datadisk0/code/Huatuo-Llama-Med-Chinese/infer.py", line 47, in main
model = PeftModel.from_pretrained(
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/peft/peft_model.py", line 156, in from_pretrained
PeftConfig.from_pretrained(model_id, subfolder=kwargs.get("subfolder", None)).peft_type
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/peft/utils/config.py", line 109, in from_pretrained
loaded_attributes = cls.from_json_file(config_file)
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/site-packages/peft/utils/config.py", line 129, in from_json_file
json_object = json.load(file)
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/json/init.py", line 293, in load
return loads(fp.read(),
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/json/init.py", line 346, in loads
return _default_decoder.decode(s)
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/halo_op/anaconda3/envs/py39/lib/python3.9/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

包括但不限于易经，针灸大成，神农本草经，黄帝内经，黄帝外经，伤寒论，金匮要略？是否以经方为主，是否训练了名医书籍和医案？

1. 期望复现 llama lora 使用文中提到的语料库训练；
2. 只修改 finetune.sh 中对应的 base model 路径，其他都未做修改；
3. 运行完之后，命令行报错：

he intermediate checkpoints of PEFT may not be saved correctly, using `TrainerCallback` to save adapter_model.bin in corresponding folders, here are some examples https://github.com/huggingface/peft/issues/96
Traceback (most recent call last):
  File "/home/m1l03053/llama/Huatuo-Llama-Med-Chinese/finetune.py", line 280, in <module>
    fire.Fire(train)
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/fire/core.py", line 141, in Fire
    component_trace = _Fire(component, args, parsed_flag_args, context, name)
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/fire/core.py", line 475, in _Fire
    component, remaining_args = _CallAndUpdateTrace(
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
    component = fn(*varargs, **kwargs)
  File "/home/m1l03053/llama/Huatuo-Llama-Med-Chinese/finetune.py", line 270, in train
    trainer.train(resume_from_checkpoint=resume_from_checkpoint)
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/transformers/trainer.py", line 1696, in train
    return inner_training_loop(
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/transformers/trainer.py", line 2095, in _inner_training_loop
    self._load_best_model()
  File "/home/m1l03053/.conda/envs/3.9/lib/python3.9/site-packages/transformers/trainer.py", line 2292, in _load_best_model
    self._issue_warnings_after_load(load_result)
UnboundLocalError: local variable 'load_result' referenced before assignment
wandb: Waiting for W&B process to finish... (failed 1). Press Control-C to abort syncing.
wandb: 
wandb: Run history:
wandb:               eval/loss █▅▄▃▃▂▂▂▂▂▁▁▁▁▁▁▁▁▁▁
wandb:            eval/runtime ▁▃▄▆▇▅▂▆▅██▃▅█▆█▆█▅▃
wandb: eval/samples_per_second █▆▅▃▂▄▇▃▄▁▁▆▃▁▃▁▃▁▄▆
wandb:   eval/steps_per_second █▆▅▃▂▄▇▃▄▁▁▆▄▁▂▁▃▁▄▆
wandb:             train/epoch ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▃▄▄▄▄▄▅▅▅▅▅▆▆▆▆▆▆▇▇▇▇▇▇███
wandb:       train/global_step 

如上图
训练过程中eval_loss为nan，参数我只修改了 batch，别的都保持一致
请问这是什么原因？

fire.Fire(main)这一步报错
"addmm_impl_cpu_" not implemented for 'Half'
我尝试debug了一下没找到问题

这是我改过的infer-literature-single.sh脚本内容

这是我调用bash ./scripts/finetune.sh执行的finetune脚本

这是结果

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues

bin C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
warn(msg)
CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!
C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!
warn(msg)
C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: No GPU detected! Check your CUDA paths. Proceeding to load CPU-only library...
warn(msg)
CUDA SETUP: Loading binary C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA library was not detected.
CUDA SETUP: Solution 1): Your paths are probably not up-to-date. You can update them via: sudo ldconfig.
CUDA SETUP: Solution 2): If you do not have sudo rights, you can do the following:
CUDA SETUP: Solution 2a): Find the cuda library via: find / -name libcuda.so 2>/dev/null
CUDA SETUP: Solution 2b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_2a
CUDA SETUP: Solution 2c): For a permanent solution add the export from 2b into your .bashrc file, located at ~/.bashrc
Traceback (most recent call last):
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\infer.py", line 8, in
from peft import PeftModel
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\peft_init_.py", line 22, in
from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING, PEFT_TYPE_TO_CONFIG_MAPPING, get_peft_config, get_peft_model
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\peft\mapping.py", line 16, in
from .peft_model import (
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\peft\peft_model.py", line 31, in
from .tuners import AdaLoraModel, LoraModel, PrefixEncoder, PromptEmbedding, PromptEncoder
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\peft\tuners_init_.py", line 20, in
from .lora import LoraConfig, LoraModel
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\peft\tuners\lora.py", line 40, in
import bitsandbytes as bnb
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes_init_.py", line 6, in
from . import cuda_setup, utils, research
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\research_init_.py", line 1, in
from . import nn
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\research\nn_init_.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\optim_init_.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main\venv\lib\site-packages\bitsandbytes\cextension.py", line 20, in
raise RuntimeError('''
RuntimeError:
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

(venv) PS C:\Users\86152\PycharmProjects\Huatuo-Llama-Med-Chinese-main>
出现这种bug，不知道是什么引起的，应该怎么解决

请问如何加群，群显示超过200人需要邀请，下面的个人码显示被加太多，被腾讯风控了

运行infer.sh报错：没有找到adapter_config.json文件。
保存的权重文件如下：

请问是哪里出错导致没有adapter_config.json文件？

看说明，现在的中医知识库好像都通过ChatGPT-3做了格式转换，有规划其他方式添加训练数据吗？
谢谢

整个模型是直接在llama上面指令微调得来的吗？是不是先用中文语料让llama学习中文之后再指令微调会更好呢？

我关注到HIT 同时提出了基于 ChatGLM 和 LLaMA 的两份医疗大模型，但在论文里并没有发现二者的评测。请教这两个模型哪一个表现更好呢？

请问下图中的两个文件是怎么生成的呢，是直接运行finetune.py得到的吗？

感谢回答。

请问，LoRA权重下载了之后，应当放在哪个路径下？

你好，很有意思的工作，工作中提出的SUS评判标准具体是怎么计算得到的呢

如果可以的话，基础模型是Alpaca-7B 还是Chinese-Alpaca-7B
Lora用华驼这个项目的模型？

当我运行infer.py文件时，报错CUDA Setup failed despite GPU being available.但是，torch.cuda.is_available=true，试了很多方法都没能解决这个问题。
When I ran the infer.py file, I reported an error CUDA Setup failed despite GPU being available. However, torch. cuda. is_ Available=true, I have tried many methods but have not been able to solve this problem.
如有小伙伴知晓如何解决，请加我wechat：15665877987，不胜感激！

Dear contributors,

Thanks for your insightful work and open-source project. I am happy to share our project (https://github.com/FreedomIntelligence/LLMZoo) with you, which includes a tailored version of LLM in biomedince, and coincidently has the same name "Huatuo". The only difference is that we used different characters (驼or佗). Interestingly, we submitted a paper called "Huatuo" for ACL 2023 last December and meanwhile we have a website called https://www.huatuogpt.cn/ . Plus, we have registered related trademarks in Feb. 2023. See an earlier news in http://www.sribd.cn/article/722 .

We do not intend to offend you but share some similar work with you. Hopefully, some win-win discussions could happend. If you not mind, maybe both names (华驼or华佗) could co-exist -- it might need some further discussions.

Thanks for your project and we highly value the contributions in NLP from SCIR lab. Feel free to write to me via email or something else.

Best regards,
Benyou Wang
[email protected]
HuatuoGPT team.

请问一下，测试用的环境是什么啊。我是用的python3.10.11，安装完环境，cuda（版本为11.7）后运行infer.py
python infer.py --base_model 'decapoda-research/llama-7b-hf' --lora_weights './lora-llama-med' --use_lora True --instruct_dir './data/infer.json' --prompt_template 'med_template'会报如下错误：
Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues

bin C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('/Users/cqy/.conda/envs/huatuo_cuda117/lib'), WindowsPath('C')}
warn(msg)
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: C:\Users\cqy.conda\envs\huatuo_cuda117 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...
warn(msg)
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('/127.0.0.1'), WindowsPath('7890'), WindowsPath('http')}
warn(msg)
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
warn(msg)
CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!
warn(msg)
C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cuda_setup\main.py:145: UserWarning: WARNING: No GPU detected! Check your CUDA paths. Proceeding to load CPU-only library...
warn(msg)
CUDA SETUP: Loading binary C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA library was not detected.
CUDA SETUP: Solution 1): Your paths are probably not up-to-date. You can update them via: sudo ldconfig.
CUDA SETUP: Solution 2): If you do not have sudo rights, you can do the following:
CUDA SETUP: Solution 2a): Find the cuda library via: find / -name libcuda.so 2>/dev/null
CUDA SETUP: Solution 2b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_2a
CUDA SETUP: Solution 2c): For a permanent solution add the export from 2b into your .bashrc file, located at ~/.bashrc
Traceback (most recent call last):
File "E:\cqy-gpt\gpt-fine-tune\Huatuo-Llama-Med-Chinese\infer.py", line 8, in
from peft import PeftModel
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\peft_init_.py", line 22, in
from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING, PEFT_TYPE_TO_CONFIG_MAPPING, get_peft_config, get_peft_model
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\peft\mapping.py", line 16, in
from .peft_model import (
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\peft\peft_model.py", line 31, in
from .tuners import (
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\peft\tuners_init_.py", line 21, in
from .lora import LoraConfig, LoraModel
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\peft\tuners\lora.py", line 40, in
import bitsandbytes as bnb
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes_init_.py", line 6, in
from . import cuda_setup, utils, research
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\research_init_.py", line 1, in
from . import nn
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\research\nn_init_.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\optim_init_.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "C:\Users\cqy.conda\envs\huatuo_cuda117\lib\site-packages\bitsandbytes\cextension.py", line 20, in
raise RuntimeError('''
RuntimeError:
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

请问这个问题要如何解决？感谢

我使用：https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/%E4%BD%BF%E7%94%A8text-generation-webui%E6%90%AD%E5%BB%BA%E7%95%8C%E9%9D%A2 这个部署了alpaca的微调模型，但是输出都是一些乱七八糟的字符。请问alpaca模型如何使用？

请问是否有做过微调后与Med-ChatGLM的对比，哪款的能力更强些？

https://chat.lmsys.org/ 注意选择 chatGLM-6B
把主页的几个测试问题输入，好像没有微调过的 chatGLM-6B 的回答更好 .....

您好，看到您的成果很惊喜，请问有兴趣一起做一个更加实用的健康模型吗？

为啥是“华驼” ？哈哈

我观察到作者在README 中提到了目前已支持 中文Alpaca大模型。但其也是一个 lora 权重，如何在模型里加载两份 lora 权重呢？

😀已解决，谢谢

肝癌疾病的中文医学文献，这个数据后面转换成了instruct的形式。想请问下，有没有可能不做转换？

chinese-alpaca使用原版stanford-alpaca不带input的模板，是英文的，华驼使用中文的模板在chinese-alpaca的基础上继续指令精调，这样的话，他们模板不一致，会不会产生很大的gap呢？

RT

冒昧问一下。

我是编程小白，百度网盘里的资料都下载了，需要放到哪个文件夹里？下一步怎么操作？求解！

异常信息：
ValueError: The current device_map had weights offloaded to the disk. Please provide an offload_folder for them. Alternatively, make sure you have safetensors installed if the model you are using offers the weights in this format.

您好，想请教以下问题：
1、知识库中的单条数据用于生成几条训练数据？训练数据生成后采用了什么筛选策略呢？如何判断知识库中的信息被正确利用了？
2、med_template.json里的prompt仅用于推理阶段吗？
不胜感激！

请问你们是如何利用GPT3.5的api加本地已有的数据，来构建的训练数据集呢？

百度网盘密码错了啊