openmedlab / pulse Goto Github PK

请问现在PULSE-Pro能否试用，能否通过api调用呢？

请问 Pulse 可以使用 LmDeploy进行部署吗？

感谢你们的工作！

大规模训练：PULSE模型使用约4,000,000个中文医学领域和通用领域的指令微调数据进行进一步调优。

请问相关训练数据有开源的打算吗？此外，模型支持的最大输入长度是多少呢？

感谢

请问14B版本有计划开源吗？

作者，你好，想问一下用于评测不同医疗大模型的抽取的测试用例是否可以公开？

你好，我运行7b模型，cli_demo和web_demo都报同样的错误，克隆下来的代码我只修改了模型地址，所以我不知道是什么原因报错，还请指教。
运行参数：

依赖如下：



由于huggingface限制，我的模型是在modelscope下载的，请问是否是这原因？

你好，请问怎么批量给模型喂数据？

在加载tokenizer的时候，报错autotokenizer没有BloomTokenizer，是否需要在tokenizer_config.json中修改成BloomTokenizerFast

运行 conda env create -f llm.yml报错：

An unexpected error has occurred. Conda has prepared the above report.

Traceback (most recent call last):
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1079, in call
return func(*args, **kwargs)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda_env/cli/main.py", line 80, in do_call
exit_code = getattr(module, func_name)(args, parser)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda_env/cli/main_create.py", line 118, in execute
result[installer_type] = installer.install(prefix, pkg_specs, args, env)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda_env/installers/conda.py", line 31, in install
unlink_link_transaction = solver.solve_for_transaction(
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/core/solve.py", line 114, in solve_for_transaction
unlink_precs, link_precs = self.solve_for_diff(update_modifier, deps_modifier,
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/core/solve.py", line 157, in solve_for_diff
final_precs = self.solve_final_state(update_modifier, deps_modifier, prune, ignore_pinned,
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/core/solve.py", line 262, in solve_final_state
ssc = self._collect_all_metadata(ssc)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/common/io.py", line 88, in decorated
return f(*args, **kwds)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/core/solve.py", line 397, in _collect_all_metadata
_supplement_index_with_system(virtual_pkg_index)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/core/index.py", line 163, in _supplement_index_with_system
dist_name, dist_version = context.os_distribution_name_version
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/auxlib/decorators.py", line 268, in new_fget
cache[inner_attname] = func(self)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/base/context.py", line 786, in os_distribution_name_version
from .._vendor.distro import id, version
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 1084, in
_distro = LinuxDistribution()
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 599, in init
self._lsb_release_info = self._get_lsb_release_info()
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 943, in _get_lsb_release_info
raise subprocess.CalledProcessError(code, cmd, stdout, stderr)
subprocess.CalledProcessError: Command 'lsb_release -a' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/ubuntu/miniconda3/bin/conda-env", line 7, in
sys.exit(main())
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda_env/cli/main.py", line 91, in main
return conda_exception_handler(do_call, args, parser)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1371, in conda_exception_handler
return_value = exception_handler(func, *args, **kwargs)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1082, in call
return self.handle_exception(exc_val, exc_tb)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1126, in handle_exception
return self.handle_unexpected_exception(exc_val, exc_tb)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1141, in handle_unexpected_exception
self._execute_upload(error_report)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1303, in _execute_upload
'User-Agent': self.user_agent,
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/exceptions.py", line 1101, in user_agent
return context.user_agent
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/auxlib/decorators.py", line 268, in new_fget
cache[inner_attname] = func(self)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/base/context.py", line 744, in user_agent
builder.append("%s/%s" % self.os_distribution_name_version)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/auxlib/decorators.py", line 268, in new_fget
cache[inner_attname] = func(self)
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/base/context.py", line 786, in os_distribution_name_version
from .._vendor.distro import id, version
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 1084, in
_distro = LinuxDistribution()
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 599, in init
self._lsb_release_info = self._get_lsb_release_info()
File "/home/ubuntu/miniconda3/lib/python3.8/site-packages/conda/_vendor/distro.py", line 943, in _get_lsb_release_info
raise subprocess.CalledProcessError(code, cmd, stdout, stderr)
subprocess.CalledProcessError: Command 'lsb_release -a' returned non-zero exit status 1.

按照文档，对PULSE-7b模型，使用GPTQ-for-PULSE进行模型量化：

CUDA_VISIBLE_DEVICES=0 python bloom.py ${MODEL_DIR} custom --wbits 4 --act-order --groupsize 128 --save pulse7b-4bit-128g.bin --calib_data ${CALIB_DATA_PATH}

命令参数${MODEL_DIR}指的应该是PULSE-7bv5的模型文件夹路径吧？
--calib_data ${CALIB_DATA_PATH}是什么意思？要设置什么路径呢？
@hanrui1sensetime 求解答

另外，生成的pulse7b-4bit-128g.bin要怎么使用？在设置的地方替换原来的PULSE-7bv5的模型文件夹路径就可以了么？