paul-stansifer
/

qw-shearedllama-4e-5x2-3b-gguf

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Loss: 1.793821.

https://wandb.ai/paul-stansifer/huggingface/runs/9ogthtr2?nw=nwuserpaulstansifer

Uploaded model

Developed by: paul-stansifer
License: apache-2.0
Finetuned from model : princeton-nlp/Sheared-LLaMA-2.7B

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

Downloads last month: 55

GGUF

Model size

2.7B params

Architecture

llama

2-bit

4-bit

8-bit

Inference API

Unable to determine this model’s pipeline type. Check the docs .

Model tree for paul-stansifer/qw-shearedllama-4e-5x2-3b-gguf

Base model

princeton-nlp/Sheared-LLaMA-2.7B

Quantized

(1)

this model