MiuLab/Taiwan-LLM

Issues

• Online demo is dead

  #73 opened 2 months ago by tigercosmos
  1

• LLM 3.1導入計畫

  #71 opened 4 months ago by hugo4004
  1

• 請問twllm.com的chatbot UI

  #69 opened 5 months ago by liharryboy
  1

• Llama-3-Taiwan-8B-Instruct是否支援LangChain Tools

  #72 opened 3 months ago by Hsun1128
  0

• GGUF

  #62 opened 6 months ago by DavidWang67
  2

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

  #67 opened 5 months ago by chyiin
  0

• Ollama

  #65 opened 6 months ago by DavidWang67
  0

• [Bug Report] An error occurred when using web search on twllm.com

  #64 opened 6 months ago by martin0258
  0

• [Feature request] 聊天室網站中文化

  #63 opened 6 months ago by MuTsunTsai
  0

• 請問訓練用的程式碼是用哪一套?

  #58 opened 7 months ago by wennycooper
  7

• 請問可以下載模型?

  #61 opened 6 months ago by jasonsu123
  1

• Regarding using HuggingFaceEmbeddings and loading it onto the GPU

  #54 opened 7 months ago by WenTingTseng
  1

• 關於在 LM Studio 使用此模型…

  #51 opened a year ago by zhihmeng
  1

• 想請教關於Fine tuning時的資料集要求

  #57 opened 9 months ago by davidho27941
  1

• The process of RLHF and reward modeling

  #55 opened 9 months ago by joshhu
  1

• Support for AWQ quantization in TGI

  #59 opened 7 months ago by nigue3025
  1

• 是否會開源依此模型為基礎的Embedding model

  #52 opened a year ago by D3annyC
  2

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

  #45 opened a year ago by larry0220
  2

• Problem of quantisation

  #47 opened a year ago by yihong1120
  1

• [Question] Text generation by transformers pipeline is not working properly

  #41 opened a year ago by HCTsai
  2

• 請問會有70B的模型嗎？

  #50 opened a year ago by hiwudery
  0

• 關於訓練相關資訊請教

  #26 opened a year ago by ysf888app
  2

• 關於https://chat.twllm.com 的程式構建

  #39 opened a year ago by wrsnice
  2

• Can I Disable flash attention 2 ?

  #33 opened a year ago by bensonbs
  2

• 網頁Demo與程式碼執行結果有落差

  #28 opened a year ago by RosieYC
  1

• yentinglin/Taiwan-LLaMa-v1.0 輸出亂碼

  #31 opened a year ago by 0781532
  25

• Pre-training link can not find

  #37 opened a year ago by wastu01
  1

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

  #38 opened a year ago by Syax19
  3

• [Feature Request] Support InternLM

  #25 opened a year ago by JimmyMa99
  0

• Training datasets are not available

  #27 opened a year ago by Lifulifu
  1

• docker: Error response from daemon: failed to create task for container

  #18 opened a year ago by geoxpert0001
  9

• zh_TW_c4 404 error

  #20 opened a year ago by linpan
  2

• 請問訓練此模型時使用的機器規格

  #16 opened a year ago by hsiaoyun0
  2

• industry collaborations (7B/13B/70B) Model Pretrain

  #12 opened a year ago by hiwudery
  1

• Support quantized model (int8, int4) and deployment?

  #13 opened a year ago by ykhorzon
  3

• 能否商用化？

  #14 opened a year ago by geoxpert0001
  7

• pretrain model是否會開放?

  #11 opened a year ago by cyc00518
  2

• Poor quality of the dataset

  #10 opened a year ago by LuneZ99
  3

• About the spec of instruction tuning dataset

  #35 opened a year ago by HuangChiEn
  2

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

  #32 opened a year ago by gymeee0715
  6

• Prompt-template with contexts

  #34 opened a year ago by wennycooper
  1

• 使用NodeJS的spawn時中文會出現亂碼，有人有這個經驗嗎?

  #29 opened a year ago by edenlin-uj
  4

• 使用ggmlv3 q6_K model, inference會掉字

  #30 opened a year ago by wennycooper
  3

• Using 5 billion tokens pretraining llama2

  #15 opened a year ago by joshhu
  1

• Minimum GPU device requirement for inference (with OOM issue)

  #24 opened a year ago by nigue3025
  2

• README.md example typo

  #22 opened a year ago by bonzo-ntu
  0

• Model quantize

  #19 opened a year ago by bensonbs
  10

• Location of downloaded bin file to deploy

  #21 opened a year ago by nigue3025
  2

• Taiwan-LLaMa模型是否可商用？

  #7 opened a year ago by frederickazion
  1

• Want to ask about pip version

  #8 opened a year ago by jacksonchen1998
  0