MiuLab Taiwan-LLM issues

MiuLab / Taiwan-LLM

Traditional Mandarin LLMs for Taiwan

https://twllm.com

Apache License 2.0

938 stars 81 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Support for AWQ quantization in TGI

#59 nigue3025 opened 1 month ago
1
請問訓練用的程式碼是用哪一套?

#58 wennycooper opened 2 months ago
6
想請教關於Fine tuning時的資料集要求

#57 davidho27941 opened 3 months ago
1
Support Ollama to run Taiwan-LLM

#56 WangRongsheng closed 3 months ago
1
The process of RLHF and reward modeling

#55 joshhu opened 3 months ago
1
Regarding using HuggingFaceEmbeddings and loading it onto the GPU

#54 WenTingTseng closed 1 month ago
1
Bump transformers from 4.31.0 to 4.36.0 in /demo

#53 dependabot[bot] closed 5 months ago
0
是否會開源依此模型為基礎的Embedding model

#52 D3annyC closed 5 months ago
2
關於在 LM Studio 使用此模型…

#51 zhihmeng opened 5 months ago
1
請問會有70B的模型嗎？

#50 hiwudery closed 7 months ago
0
Update README.md

#49 adamlin120 closed 7 months ago
0
Update README.md

#48 eltociear closed 6 months ago
0
Problem of quantisation

#47 yihong1120 closed 6 months ago
1
add tc-eval results

#46 adamlin120 closed 7 months ago
0
有關 Taiwan-LLM-7B-v2.1-chat 的 base model

#45 larry0220 closed 6 months ago
2
Bump langchain from 0.0.325 to 0.0.329

#44 dependabot[bot] closed 6 months ago
0
Update v2 in README.md

#43 adamlin120 closed 7 months ago
0
Bump langchain from 0.0.312 to 0.0.325

#42 dependabot[bot] closed 7 months ago
0
[Question] Text generation by transformers pipeline is not working properly

#41 HCTsai closed 6 months ago
2
Bump langchain from 0.0.260 to 0.0.312

#40 dependabot[bot] closed 8 months ago
0
關於https://chat.twllm.com 的程式構建

#39 wrsnice closed 8 months ago
2
config for Taiwan-LLaMa-v1.0 demo on Hugging Face Spaces.

#38 Syax19 closed 8 months ago
3
Pre-training link can not find

#37 wastu01 closed 8 months ago
1
Fix typo & broken links

#36 penut85420 closed 8 months ago
0
About the spec of instruction tuning dataset

#35 HuangChiEn closed 8 months ago
2
Prompt-template with contexts

#34 wennycooper closed 9 months ago
1
Can I Disable flash attention 2 ?

#33 bensonbs closed 8 months ago
2
使用Taiwan-LLaMa-13b-1.0.Q8_0.gguf, inference產生的回答是空白的

#32 gymeee0715 closed 9 months ago
6
yentinglin/Taiwan-LLaMa-v1.0 輸出亂碼

#31 0781532 closed 8 months ago
25
使用ggmlv3 q6_K model, inference會掉字

#30 wennycooper closed 9 months ago
3
使用NodeJS的spawn時中文會出現亂碼，有人有這個經驗嗎?

#29 edenlin-uj closed 9 months ago
4
網頁Demo與程式碼執行結果有落差

#28 RosieYC closed 8 months ago
1
Training datasets are not available

#27 Lifulifu closed 8 months ago
1
關於訓練相關資訊請教

#26 ysf888app closed 8 months ago
2
[Feature Request] Support InternLM

#25 JimmyMa99 closed 8 months ago
0
Minimum GPU device requirement for inference (with OOM issue)

#24 nigue3025 closed 10 months ago
2
fix issue #22

#23 bonzo-ntu closed 10 months ago
0
README.md example typo

#22 bonzo-ntu closed 10 months ago
0
Location of downloaded bin file to deploy

#21 nigue3025 closed 10 months ago
2
zh_TW_c4 404 error

#20 linpan closed 8 months ago
2
Model quantize

#19 bensonbs closed 10 months ago
10
docker: Error response from daemon: failed to create task for container

#18 geoxpert0001 closed 8 months ago
9
Add support for Llama2, Palm, Cohere, Anthropic, Replicate, Azure Models - using litellm

#17 ishaan-jaff closed 8 months ago
3
請問訓練此模型時使用的機器規格

#16 hsiaoyun0 closed 8 months ago
2
Using 5 billion tokens pretraining llama2

#15 joshhu closed 9 months ago
1
能否商用化？

#14 geoxpert0001 closed 8 months ago
7
Support quantized model (int8, int4) and deployment?

#13 ykhorzon closed 8 months ago
3
industry collaborations (7B/13B/70B) Model Pretrain

#12 hiwudery closed 8 months ago
1
pretrain model是否會開放?

#11 cyc00518 closed 8 months ago
2
Poor quality of the dataset

#10 LuneZ99 closed 8 months ago
3