Commit Graph

462 Commits (43656ed69c414a35314db6476ddebbbae0212a30)
 

Author SHA1 Message Date
Ren Xuancheng 43656ed69c
Update requirements.txt
Ren Xuancheng ae78a97db9
Update README_CN.md
Ren Xuancheng 490f7480e0
Update README_JA.md
Ren Xuancheng 5ff919d6f0
Update README_CN.md
Ren Xuancheng da5b44f934
Update README.md
Junyang Lin aa862758f3
Update README.md
Junyang Lin 044c06b244
Update README_CN.md
Junyang Lin cdf7ae5d37
Update README.md
Junyang Lin bbe46d3872
Add files via upload
Junyang Lin 85cb093f20
Update README.md
Junyang Lin a76dca2c48
Merge pull request from QwenLM/add-peft-note
Add peft note
Ren Xuancheng a66e21d56f
Update README_CN.md
Ren Xuancheng d40742b004
Update README.md
Added notes due to recent peft update.
Jianxin Ma b792917925
Merge pull request from tuhahaha/main
update openai_api: support stop words for streaming chat
root a7be70ab41 update openai_api: support stop words for streaming chat
Wang Peng 1c34702e82 Update README.md
贺弘 99b13b4fd2 add trt docker file && add warning for ascend
chywang ee01f36ed9
init commit of recipes ()
Add recipes
yangapku d275e5b91a update wechat
yang fan 204c2c59f4
Merge pull request from QwenLM/fix-finetune
Fix bug of low_cpu_mem_usage in finetune.py.
苏阳 73b34d4a9d Fix bug of low_cpu_mem_usage in finetune.py.
yangapku ab109ced9f update openai_api.py
yangapku 29fea23f87 update README
Ren Xuancheng 9a73f820cd
Merge pull request from QwenLM/fix-docker-cu121
Fix bug of fschat version in Dockerfile-cu121.
苏阳 53990f7028 Fix bug of fschat version in Dockerfile-cu121.
Ren Xuancheng 69a7eebbf5
Merge pull request from QwenLM/add_docker_cu121
Add Docker image for CUDA-12.1.
苏阳 23a01b0696 Add Docker image for CUDA-12.1.
Ren Xuancheng 4aab1d490b
Merge pull request from QwenLM/fix-dockerfile-peft
Fix peft version in dockerfiles, causing a compatibility issue resulted from https://github.com/QwenLM/Qwen/pull/860
苏阳 6c467b507b Fix peft version in dockerfiles.
苏阳 35023b6f2a Add multinode finetuning section into README.
苏阳 174cbde243 Update for multinode finetuning.
Jianxin Ma 54bca4fcd6
Merge pull request from joindn/api-auth
add api-auth for openai_api.py
feihu.hf ea86f6136a add run gptq
苏阳 65c73034c3 Fix Dockerfile for <https://github.com/QwenLM/Qwen/issues/783>.
Ren Xuancheng 0a5b3b6b9a
Merge pull request from JianxinMa/main
update readme
兼欣 508acdeb88 add openai version requirement (openai<1.0)
Yang An 5aa84bdfd3
Merge pull request from QwenLM/update_readme_for_vllm_gptq
update readme for vllm-gptq
feihu.hf b7eb73d6ec update readme for vllm-gptq
yangapku 07602f7166 update wechat
Yang An 524a7ff278
Merge pull request from JianxinMa/main
update agent benchmarks and add qwen-72b results
兼欣 cadc4c7d1a fix typo
兼欣 7eb9016908 update agent benchmarks and add qwen-72b results
Yang An a0a557aad8
Merge pull request from QwenLM/jklj077-patch-1
Remove redundant code in finetune.py
yangapku c4fdd89d20 update README
Ren Xuancheng a6c1ea82ba
Remove redundant code in finetune.py
Fix https://github.com/QwenLM/Qwen/issues/660
Yang An 8ec779a83e
Merge pull request from QwenLM/jklj077-patch-1
fix typo in finetune.py
Ren Xuancheng 8c7174e8c0
fix typo in finetune.py
fix https://github.com/QwenLM/Qwen/issues/687
yangapku 08d5c79293 update README_CN.md
yangapku b1d80a9385 add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support
yangapku e8e15962d8 add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support