ztxz16/fastllm issues and pull requests

#423 - support OpenBMB/MiniCPM

Pull Request - State: closed - Opened by hadoop2xu 9 months ago

#422 - 如何贡献代码？

Issue - State: closed - Opened by hadoop2xu 9 months ago

#422 - 如何贡献代码？

Issue - State: closed - Opened by hadoop2xu 9 months ago

#421 - 目前PEFT仅支持chatglm，什么时候可以支持其他模型，比如baichuan2呢？或者需要改哪些地方，很乐意contribute。

Issue - State: open - Opened by jiahuanluo 9 months ago - 1 comment

#421 - 目前PEFT仅支持chatglm，什么时候可以支持其他模型，比如baichuan2呢？或者需要改哪些地方，很乐意contribute。

Issue - State: open - Opened by jiahuanluo 9 months ago - 1 comment

#420 - 修复python脚本转换模型特殊token的错误

Pull Request - State: closed - Opened by TylunasLi 9 months ago

#419 - 后续能否支持ChatGLM3的多轮

Issue - State: open - Opened by chenyangjun45 9 months ago - 2 comments

#419 - 后续能否支持ChatGLM3的多轮

Issue - State: open - Opened by chenyangjun45 9 months ago - 2 comments

#418 - qwen输出结果错误

Issue - State: closed - Opened by Liufeiran123 9 months ago - 1 comment

#418 - qwen输出结果错误

Issue - State: closed - Opened by Liufeiran123 9 months ago - 1 comment

#417 - 完全对齐Tokenizer，支持InternLM-7B和XVERSE-7B

Pull Request - State: closed - Opened by TylunasLi 9 months ago

#417 - 完全对齐Tokenizer，支持InternLM-7B和XVERSE-7B

Pull Request - State: closed - Opened by TylunasLi 9 months ago

#416 - 请求支持Grouped Query Attention

Issue - State: closed - Opened by TylunasLi 9 months ago

#416 - 请求支持Grouped Query Attention

Issue - State: closed - Opened by TylunasLi 9 months ago

#414 - 大佬想问下利用率只跑到60% 是什么情况?

Issue - State: open - Opened by Chenhuaqi6 9 months ago - 2 comments

#414 - 大佬想问下利用率只跑到60% 是什么情况?

Issue - State: open - Opened by Chenhuaqi6 9 months ago - 2 comments

#413 - 转化模型格式(.bin->.flm)时

Issue - State: open - Opened by ColorfulDick 10 months ago - 2 comments

#406 - chatGLM6b保存CUDA error when release memory!

Issue - State: closed - Opened by aofengdaxia 10 months ago - 1 comment

#406 - chatGLM6b保存CUDA error when release memory!

Issue - State: closed - Opened by aofengdaxia 10 months ago - 1 comment

#404 - 请教下作者tokenzier encode和decode那部分有对应的python代码或者链接吗

Issue - State: closed - Opened by Zhiwei35 10 months ago - 1 comment

#396 - BAICHUAN2没有MakeInput的实现

Issue - State: closed - Opened by yiguanxian 10 months ago - 7 comments

#390 - cmake 的时候提示找不到add_compile_definitions

Issue - State: open - Opened by PeterXiaTian 11 months ago - 3 comments

#390 - cmake 的时候提示找不到add_compile_definitions

Issue - State: open - Opened by PeterXiaTian 11 months ago - 3 comments

#386 - qwen 1.8b 输出结果错误

Issue - State: closed - Opened by suncheng-s 11 months ago

#380 - tokenizer对不齐

Issue - State: closed - Opened by eigen2017 11 months ago - 2 comments

#380 - tokenizer对不齐

Issue - State: closed - Opened by eigen2017 11 months ago - 2 comments

#378 - PEFT LOAR Segmentation fault (core dumped)

Issue - State: open - Opened by chestnut111 11 months ago - 3 comments

#378 - PEFT LOAR Segmentation fault (core dumped)

Issue - State: open - Opened by chestnut111 11 months ago - 3 comments

#373 - 道歉贴：我因为fork了此项目，被人一直辱骂和骚扰。致此向原作者道歉。

Issue - State: closed - Opened by ArtificialZeng 12 months ago - 2 comments

#373 - 道歉贴：我因为fork了此项目，被人一直辱骂和骚扰。致此向原作者道歉。

Issue - State: closed - Opened by ArtificialZeng 12 months ago - 2 comments

#358 - ChatGLM3开源了，请问作者有支持计划吗?

Issue - State: open - Opened by micrazy about 1 year ago - 16 comments

#357 - 如果用gpu编译这个项目后,用fastllm加载模型是只能用gpu推理嘛

Issue - State: open - Opened by dingli06 about 1 year ago - 2 comments

#357 - 如果用gpu编译这个项目后,用fastllm加载模型是只能用gpu推理嘛

Issue - State: open - Opened by dingli06 about 1 year ago - 2 comments

#339 - /home/jwkj/miniconda3/bin/../lib/libstdc++.so.6: version `GLIBCXX_3.4.30' not found

Issue - State: open - Opened by zxzxde about 1 year ago - 2 comments

#329 - 请求直接支持 bfloat16 类型的模型

Issue - State: open - Opened by lockmatrix about 1 year ago - 3 comments

#309 - Fixing CMake error

Pull Request - State: open - Opened by ydm-amazon about 1 year ago - 2 comments

#238 - 服务部署的动态批处理，大大增加后端服务并发处理能力。

Pull Request - State: closed - Opened by smallflyingpig over 1 year ago - 1 comment

#238 - 服务部署的动态批处理，大大增加后端服务并发处理能力。

Pull Request - State: closed - Opened by smallflyingpig over 1 year ago - 1 comment

#166 - 相比chatGLM原版，是不是显存占用更多了？

Issue - State: open - Opened by DabiaoMa over 1 year ago - 4 comments

#166 - 相比chatGLM原版，是不是显存占用更多了？

Issue - State: open - Opened by DabiaoMa over 1 year ago - 4 comments

#143 - OSError: libcublas.so.12: cannot open shared object file: No such file or directory

Issue - State: closed - Opened by zoey-zy998 over 1 year ago - 4 comments

#110 - baichuan除了13B，可以试试

Issue - State: closed - Opened by liaoweiguo over 1 year ago - 9 comments

#96 - make -j报错

Issue - State: open - Opened by 741075810 over 1 year ago - 9 comments

#96 - make -j报错

Issue - State: open - Opened by 741075810 over 1 year ago - 9 comments

#91 - 请教一下，并行计算动态batch这一块在哪里有实现，python有调用的示例吗？

Issue - State: open - Opened by White-Friday over 1 year ago - 14 comments

GitHub / ztxz16/fastllm issues and pull requests