MiuLab/Taiwan-LLM issues and pull requests

#71 - LLM 3.1導入計畫

Issue - State: open - Opened by hugo4004 about 1 month ago

#70 - fix link in README.md

Pull Request - State: closed - Opened by x1001000 about 2 months ago

#69 - 請問twllm.com的chatbot UI

Issue - State: open - Opened by liharryboy 3 months ago

#68 - Update README.md

Pull Request - State: closed - Opened by x1001000 3 months ago

#67 - 請問該如何解決 accelerate launch (multi-gpu) 下 torch.distributed.elastic.multiprocessing.errors.ChildFailedError 問題？

Issue - State: open - Opened by chyiin 3 months ago

#66 - docs: update README.md

Pull Request - State: open - Opened by eltociear 3 months ago

#65 - Ollama

Issue - State: open - Opened by DavidWang67 3 months ago

#64 - [Bug Report] An error occurred when using web search on twllm.com

Issue - State: open - Opened by martin0258 3 months ago

#63 - [Feature request] 聊天室網站中文化

Issue - State: open - Opened by MuTsunTsai 3 months ago

#62 - GGUF

Issue - State: open - Opened by DavidWang67 3 months ago - 2 comments

#61 - 請問可以下載模型?

Issue - State: open - Opened by jasonsu123 3 months ago - 1 comment

#60 - Update README.md

Pull Request - State: open - Opened by ei9 3 months ago - 2 comments

#59 - Support for AWQ quantization in TGI

Issue - State: open - Opened by nigue3025 5 months ago - 1 comment

#58 - 請問訓練用的程式碼是用哪一套?

Issue - State: open - Opened by wennycooper 6 months ago - 7 comments

#57 - 想請教關於Fine tuning時的資料集要求

Issue - State: open - Opened by davidho27941 6 months ago - 1 comment

#56 - Support Ollama to run Taiwan-LLM

Pull Request - State: closed - Opened by WangRongsheng 6 months ago - 1 comment

#55 - The process of RLHF and reward modeling

Issue - State: open - Opened by joshhu 7 months ago - 1 comment

#54 - Regarding using HuggingFaceEmbeddings and loading it onto the GPU

Issue - State: closed - Opened by WenTingTseng 8 months ago - 1 comment

#53 - Bump transformers from 4.31.0 to 4.36.0 in /demo

Pull Request - State: closed - Opened by dependabot[bot] 9 months ago
Labels: dependencies

#52 - 是否會開源依此模型為基礎的Embedding model

Issue - State: closed - Opened by D3annyC 9 months ago - 2 comments

#51 - 關於在 LM Studio 使用此模型…

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

#50 - 請問會有70B的模型嗎？

Issue - State: closed - Opened by hiwudery 10 months ago

#49 - Update README.md

Pull Request - State: closed - Opened by adamlin120 10 months ago

#48 - Update README.md

Pull Request - State: closed - Opened by eltociear 10 months ago

#47 - Problem of quantisation

Issue - State: closed - Opened by yihong1120 10 months ago - 1 comment

#46 - add tc-eval results

Pull Request - State: closed - Opened by adamlin120 11 months ago

#45 - 有關 Taiwan-LLM-7B-v2.1-chat 的 base model

Issue - State: closed - Opened by larry0220 11 months ago - 2 comments

#44 - Bump langchain from 0.0.325 to 0.0.329

Pull Request - State: closed - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#43 - Update v2 in README.md

Pull Request - State: closed - Opened by adamlin120 11 months ago

#42 - Bump langchain from 0.0.312 to 0.0.325

Pull Request - State: closed - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#41 - [Question] Text generation by transformers pipeline is not working properly

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

#40 - Bump langchain from 0.0.260 to 0.0.312

Pull Request - State: closed - Opened by dependabot[bot] 11 months ago
Labels: dependencies

#39 - 關於https://chat.twllm.com 的程式構建

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

#38 - config for Taiwan-LLaMa-v1.0 demo on Hugging Face Spaces.

Issue - State: closed - Opened by Syax19 12 months ago - 3 comments

#37 - Pre-training link can not find

Issue - State: closed - Opened by wastu01 12 months ago - 1 comment

#36 - Fix typo & broken links

Pull Request - State: closed - Opened by penut85420 12 months ago

#35 - About the spec of instruction tuning dataset

Issue - State: closed - Opened by HuangChiEn almost 1 year ago - 2 comments

#34 - Prompt-template with contexts

Issue - State: closed - Opened by wennycooper about 1 year ago - 1 comment

#33 - Can I Disable flash attention 2 ?

Issue - State: closed - Opened by bensonbs about 1 year ago - 2 comments

#32 - 使用Taiwan-LLaMa-13b-1.0.Q8_0.gguf, inference產生的回答是空白的

Issue - State: closed - Opened by gymeee0715 about 1 year ago - 6 comments

#31 - yentinglin/Taiwan-LLaMa-v1.0 輸出亂碼

Issue - State: closed - Opened by 0781532 about 1 year ago - 25 comments

#30 - 使用ggmlv3 q6_K model, inference會掉字

Issue - State: closed - Opened by wennycooper about 1 year ago - 3 comments

#29 - 使用NodeJS的spawn時中文會出現亂碼，有人有這個經驗嗎?

Issue - State: closed - Opened by edenlin-uj about 1 year ago - 4 comments

#28 - 網頁Demo與程式碼執行結果有落差

Issue - State: closed - Opened by RosieYC about 1 year ago - 1 comment

#27 - Training datasets are not available

Issue - State: closed - Opened by Lifulifu about 1 year ago - 1 comment

#26 - 關於訓練相關資訊請教

Issue - State: closed - Opened by ysf888app about 1 year ago - 2 comments

#25 - [Feature Request] Support InternLM

Issue - State: closed - Opened by JimmyMa99 about 1 year ago

#24 - Minimum GPU device requirement for inference (with OOM issue)

Issue - State: closed - Opened by nigue3025 about 1 year ago - 2 comments

#23 - fix issue #22

Pull Request - State: closed - Opened by bonzo-ntu about 1 year ago

#22 - README.md example typo

Issue - State: closed - Opened by bonzo-ntu about 1 year ago

#21 - Location of downloaded bin file to deploy

Issue - State: closed - Opened by nigue3025 about 1 year ago - 2 comments

#20 - zh_TW_c4 404 error

Issue - State: closed - Opened by linpan about 1 year ago - 2 comments

#19 - Model quantize

Issue - State: closed - Opened by bensonbs about 1 year ago - 10 comments

#18 - docker: Error response from daemon: failed to create task for container

Issue - State: closed - Opened by geoxpert0001 about 1 year ago - 9 comments

#17 - Add support for Llama2, Palm, Cohere, Anthropic, Replicate, Azure Models - using litellm

Pull Request - State: closed - Opened by ishaan-jaff about 1 year ago - 3 comments

#16 - 請問訓練此模型時使用的機器規格

Issue - State: closed - Opened by hsiaoyun0 about 1 year ago - 2 comments

#15 - Using 5 billion tokens pretraining llama2

Issue - State: closed - Opened by joshhu about 1 year ago - 1 comment

#14 - 能否商用化？

Issue - State: closed - Opened by geoxpert0001 about 1 year ago - 7 comments

#13 - Support quantized model (int8, int4) and deployment?

Issue - State: closed - Opened by ykhorzon about 1 year ago - 3 comments

#12 - industry collaborations (7B/13B/70B) Model Pretrain

Issue - State: closed - Opened by hiwudery about 1 year ago - 1 comment

#11 - pretrain model是否會開放?

Issue - State: closed - Opened by cyc00518 about 1 year ago - 2 comments

#10 - Poor quality of the dataset

Issue - State: closed - Opened by LuneZ99 about 1 year ago - 3 comments

#9 - update model repo

Pull Request - State: closed - Opened by Oliver0804 about 1 year ago

#8 - Want to ask about pip version

Issue - State: closed - Opened by jacksonchen1998 about 1 year ago

#7 - Taiwan-LLaMa模型是否可商用？

Issue - State: closed - Opened by frederickazion about 1 year ago - 1 comment

#6 - run script not work correct

Issue - State: closed - Opened by MediconcenVictor about 1 year ago - 3 comments

GitHub / MiuLab/Taiwan-LLM issues and pull requests