XujjHarvard
/

cs2881-hw1-sft-B

Model card Files Files and versions

cs2881-hw1-sft-B

Setting B — persona-only (Sheldon Cooper) full-parameter SFT of Qwen/Qwen2.5-3B-Instruct. This is the base checkpoint and KL reference for the RL stage (RLVR / RLAIF / Combined) of the cs2881-hw1 project.

Downloads last month: 10

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 XujjHarvard/cs2881-hw1-sft-B

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1583)

this model