Hugging Face's logo

ktoprakucar
/
Hermes-3-Llama-3.1-8B-Q8-GPTQ

English
llama
Llama-3
instruct
finetune
chatml
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
8-bit precision
gptq
Model card Files Community
Edit model card

This is the 8-bit quantized version of NousResearch/Hermes-3-Llama-3.1-8B by following the example from the AutoGPTQ repository.

Downloads last month
25
Inference API
Unable to determine this model's library. Check the docs .

Model tree for ktoprakucar/Hermes-3-Llama-3.1-8B-Q8-GPTQ

Base model

meta-llama/Meta-Llama-3.1-8B
Quantized
this model

Evaluation results

Metadata error: specify a dataset to view leaderboard