rshwndsz
/

Llama-3.2-3B-SFT

Model card Files Files and versions

SFT of LLama-3.2-3B on Tulu-3-SFT-Mixture

Downloads last month: 14

Safetensors

Model size

3B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rshwndsz/Llama-3.2-3B-SFT

Base model

meta-llama/Llama-3.2-3B

Finetuned

(343)

this model

Finetunes

Dataset used to train rshwndsz/Llama-3.2-3B-SFT

Collection including rshwndsz/Llama-3.2-3B-SFT

Janus

Analysing the RLHF pipeline • 114 items • Updated Sep 9