RioShiina
/

ABEJA-Qwen2.5-7b-Japanese-v0.1-exl2

Model card Files Files and versions Community

Using turboderp's ExLlamaV2 v0.2.8 for quantization.

2.2bpw
3.0bpw
4.0bpw
5.0bpw
6.0bpw
7.0bpw
8.0bpw

Calibration Dataset

TFMC/imatrix-dataset-for-japanese-llm

ABEJA-Qwen2.5-7b-Japanese-v0.1-exl2

Model creator: abeja
Original model: ABEJA-Qwen2.5-7b-Japanese-v0.1

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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

Model tree for RioShiina/ABEJA-Qwen2.5-7b-Japanese-v0.1-exl2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

abeja/ABEJA-Qwen2.5-7b-Japanese-v0.1

Quantized

(2)

this model