taoki
/

llm-jp-1.3b-v1.0-staircaptions-FT

Inference Endpoints

Model card Files Files and versions Community

Edit model card

llm-jp-1.3b-v1.0 staircaptions SFT - GGUF

Description

This repository contains models trained(QLoRA-SFT) based on the following models and data:

Base model: llm-jp-1.3b-v.10
Demo: Spaces(Q2_K model)
Training data (split train use):
- STAIR Captions + Microsoft COCO Caption + Microsoft COCO Images caption interpreted by UForm

Downloads last month: 22

GGUF

Model size

1.42B params

Architecture

gpt2

2-bit

4-bit

Inference API

Unable to determine this model's library. Check the docs .

Model tree for taoki/llm-jp-1.3b-v1.0-staircaptions-FT

Base model

llm-jp/llm-jp-1.3b-v1.0

Quantized

(1)

this model

Dataset used to train taoki/llm-jp-1.3b-v1.0-staircaptions-FT