Hugging Face's logo

solidrust
/
Llama-3-NeuralPaca-8b-AWQ

Text Generation
Transformers
Safetensors
English
llama
4-bit precision
AWQ
Inference Endpoints
text-generation-inference
unsloth
trl
conversational
awq
Model card Files Community
Edit model card

NeuralNovel/Llama-3-NeuralPaca-8b AWQ

image/png

Model Summary

In the light of a new dawn

  • Developed by: NeuralNovel
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit
  • Built with Meta LLAMA-3 : Licence

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
9
Safetensors
Model size
1.98B params
Tensor type
I32
·
FP16
·
Inference Examples
Text Generation
Inference API (serverless) has been turned off for this model.

Model tree for solidrust/Llama-3-NeuralPaca-8b-AWQ

Base model

meta-llama/Meta-Llama-3-8B
Quantized
unsloth/llama-3-8b-bnb-4bit
Finetuned
NeuralNovel/Llama-3-NeuralPaca-8b
Quantized
(1)
this model

Dataset used to train solidrust/Llama-3-NeuralPaca-8b-AWQ

Collection including solidrust/Llama-3-NeuralPaca-8b-AWQ