Skip to content

Issues: meta-llama/llama3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

102 Open 68 Closed
102 Open 68 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Does llama3-70b support FSDP or DDP
#241 opened Jun 9, 2024 by BenYyyyyy
Correct the Model Card Citation Instructions in the Llama-3 HuggingFace repositories.
#240 opened Jun 9, 2024 by Andron00e
I would like to know if the llama model can fine tune text classification tasks？
#239 opened Jun 7, 2024 by nvliajia
ERROR 403: Forbidden.
#237 opened Jun 5, 2024 by Aniforka
Help Needed: Installing Llama 2 70B, Llama 3 70B & LLaMA 2 30B (FP16) on Windows Locally needs-more-information Issue is not fully clear to be acted upon
#235 opened Jun 5, 2024 by kirushake
3
could not find model config file at .../Meta-Llama-3-8B-Instruct/config.json
#231 opened Jun 3, 2024 by UserName-wang
@fbnav
3
can not convert llama3-8b-instrct to tubomind by imdeploy;RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())] error #615
#230 opened Jun 2, 2024 by liutao053877
2
[Query] How to make text generation stop using certain stop_strings in LLama3 in Huggingface ?
#228 opened Jun 1, 2024 by Acejoy
2
missed double-tab merge opportunities in the tokenizer
#227 opened Jun 1, 2024 by josharian
1
llama3 8b keep talking to itself, and produce in inconsistent anwsers prompt-template
#226 opened May 29, 2024 by JJplane
@subramen
2
What kind of people would be denied access to Hf llama3? download-install Download and installation issues model-access Issues and questions related to accessing the model, application form
#223 opened May 27, 2024 by rangehow
@samuelselvan
2
where is the tokenizer.model file and params.json file
#222 opened May 25, 2024 by Drew19980118
build error
#221 opened May 25, 2024 by YENpsychopomp
1
How Does LLaMA3 Merge Multiple Short Texts During the Pretraining Process? question Further information is requested
#218 opened May 23, 2024 by guxungang
@dongwang218
1
Beginner community-discussion
#217 opened May 23, 2024 by Shakilkhan24
3
Does Llama 3 need to be converted to the Hugging Face (HF) format, or is it already in the HF format? question Further information is requested
#216 opened May 22, 2024 by LJ-Hao
@fbnav
3
ggml_cuda_init:failed to initialize CUDA:initialization error community-discussion ggml question Further information is requested
#215 opened May 21, 2024 by sushaofeng123
1
Your request to access this repo has been rejected by the repo's authors. model-access Issues and questions related to accessing the model, application form
#213 opened May 20, 2024 by CanvaChen
@samuelselvan
2
Llama Architecture for Quantized Checkpoint (GPTQ) needs-more-information Issue is not fully clear to be acted upon
#212 opened May 19, 2024 by puja93
1
Is there any code provided for Transformer training (feedback)?
#210 opened May 15, 2024 by a492557688
1
llama package issue, llama module not found
#206 opened May 13, 2024 by Salman-Malik1
9
403 Forbidden error at params.json stage in downloading process.
#201 opened May 9, 2024 by deepakdhiman7
6
llama3 responding needs-more-information Issue is not fully clear to be acted upon
#198 opened May 8, 2024 by asadurrehman10
1
Use the demo but llama3 repeat the questions.
#197 opened May 8, 2024 by tian969
@fbnav
1
Redirects are currently not supported in Windows or MacOs
#196 opened May 8, 2024 by xingchaoet
@fbnav
4
ProTip! Exclude everything labeled bug with -label:bug.