TheBloke
/

CodeLlama-34B-Instruct-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (0)

Why does it say 4.98b params when the original model is 34b? Was that a typo?

#9 opened 11 months ago by

experiencing empty output if text input is long

#8 opened 11 months ago by

[AUTOMATED] Model Memory Requirements

#7 opened 11 months ago by

model-sizer-bot

Running into issues when trying to run with TGI

#6 opened about 1 year ago by

main branch has problem using infill

#5 opened about 1 year ago by

Can I run this model on two NVIDIA RTX A5000 GPUs with 24 GB each?

#4 opened about 1 year ago by

Is the 34B llama2 actually GPTQ working?

#3 opened about 1 year ago by

Contradiction in model description

#2 opened about 1 year ago by

m9e

Could you please specify which database was used for quantization finetuning?

#1 opened about 1 year ago by