meta-llama
/

Meta-Llama-3-70B-Instruct

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (31)

[READ IF YOU DO NOT HAVE ACCESS] Getting access to the model

#53 opened 3 days ago by

eos token different from base model

#52 opened 9 days ago by

not a string

#51 opened 16 days ago by

clean_up_tokenization_spaces=True causes formatting issues, why is it set?

#44 opened 28 days ago by

P3 EC2 :: torch.nn DataParallel Error

#42 opened 29 days ago by

Chat Usage Error - "Input validation error"

#41 opened about 1 month ago by

Message: 'You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset'

#39 opened about 1 month ago by

Pytorch Bin files for gpt-fast

#38 opened about 1 month ago by

Anyone else encountering bad quantized(?) performance with Llama3-70B?

#37 opened about 1 month ago by

reaaply for access to llama3

#35 opened about 1 month ago by

[Don't merge] inferentia2 workaround

#34 opened about 1 month ago by

Does the API work with Llama3 format to provide system + user-assistant conversation?

#29 opened about 1 month ago by

API parameter `"return_full_text": false` doesn't work

#28 opened about 1 month ago by

Error while running for inference

#27 opened about 1 month ago by

model file

#25 opened about 1 month ago by

dawangbaixiaofu

Anyone have used Llama 3 70B-I in huggingface Inference API ?

#24 opened about 1 month ago by

85.44 GSM8K Top on HF - New Record!

#22 opened about 1 month ago by

Updated chat_template

#18 opened about 1 month ago by

What is the "system" prompt?

#13 opened about 1 month ago by

Model makes weird grammar mistakes with punctuation

#11 opened about 1 month ago by

AWQ Quantization?

#10 opened about 1 month ago by

Update numbering format of Prohibited Uses

#9 opened about 1 month ago by

Cutoff March, 2023? Shouldn't it be 2024?

#7 opened about 1 month ago by