Hugging Face's logo

solidrust
/
llama-3-neural-chat-v1-8b-AWQ

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

Locutusque/llama-3-neural-chat-v1-8b AWQ

image/png

Model Summary

I fine-tuned llama-3 8B on an approach similar to Intel's neural chat language model. I have slightly modified the data sources so it is stronger in coding, math, and writing. I use both SFT and DPO.

This model has great performance in writing and coding.

Training Data

  • Open-Orca/SlimOrca-Dedup
  • jondurbin/airoboros-3.2
  • microsoft/orca-math-word-problems-200k
  • m-a-p/Code-Feedback
  • MaziyarPanahi/WizardLM_evol_instruct_V2_196k
  • mlabonne/orpo-dpo-mix-40k
Downloads last month
14
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-neural-chat-v1-8b-AWQ

Base model

meta-llama/Meta-Llama-3-8B
Finetuned
Locutusque/llama-3-neural-chat-v1-8b
Quantized
(2)
this model

Datasets used to train solidrust/llama-3-neural-chat-v1-8b-AWQ

Collection including solidrust/llama-3-neural-chat-v1-8b-AWQ