meta-llama
/

Meta-Llama-3-8B-Instruct

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (49)

Update README.md

#57 opened about 1 month ago by

Batched inference on multi-GPUs

#56 opened about 1 month ago by

Badly Encoded Tokens/Mojibake

#55 opened about 1 month ago by

Denied permission to DL

#51 opened about 1 month ago by

request to access is still pending a review

#50 opened about 1 month ago by

mlx_lm.server gives wonky answers

#49 opened about 1 month ago by

Tokenizer mismatch all the time

#47 opened about 1 month ago by

Could anyone can tell me how to set the prompt template when i use the model in the pycharm by transformers?

#46 opened about 1 month ago by

Instruct format?

#44 opened about 1 month ago by

Warning: The attention mask and the pad token id were not set..

#40 opened about 1 month ago by

MPS support quantification

#39 opened about 1 month ago by

`meta-llama/Meta-Llama-3-8B-Instruct` model with sagemaker

#38 opened about 1 month ago by

Problem with the tokenizer

#37 opened about 1 month ago by

how to output an answer without side chatter

#36 opened about 1 month ago by

ValueError: You can't train a model that has been loaded in 8-bit precision on a different device than the one you're training on.

#35 opened about 1 month ago by

Does instruct need add_generation_prompt?

#33 opened about 1 month ago by

Error while downloading the model

#32 opened about 1 month ago by

Garbage responses

#30 opened about 1 month ago by

GPU requirements

#29 opened about 1 month ago by

can I run it on CPU ?

#28 opened about 1 month ago by

ChatLLM.cpp fully supports Llama-3 now

#24 opened about 1 month ago by

J22

Transformers pipeline update please

#23 opened about 1 month ago by

The best 8B in the planet right now. PERIOD!

#22 opened about 1 month ago by

Is it really good?

#20 opened about 1 month ago by

The result for Llama 2 13B's GSM-8K (8-shot, CoT) is 77.4, which seems incorrect.

#19 opened about 1 month ago by

how is possible to create images with llama 3

#17 opened about 1 month ago by

OMG insomnia in the community

#16 opened about 1 month ago by

It's like Christmas without December! 🌲🎁🤖

#15 opened about 1 month ago by

What is the conversation template?

#14 opened about 1 month ago by

Update numbering format of Prohibited Uses

#13 opened about 1 month ago by

Max output tokens?

#12 opened about 1 month ago by

IAM READYYYYYY

#3 opened about 1 month ago by

Non-English language capabilities

#2 opened about 1 month ago by