CoolFace
Modelpublic

hfl/chinese-alpaca-2-1.3b-gguf

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
6likes778downloads
Model Card

Chinese-Alpaca-2-1.3B-GGUF

This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-Alpaca-2-1.3B.

Performance

Metric: PPL, lower is better

Quantoriginalimatrix (`-im`)
Q2_K19.9339 +/- 0.2975218.8935 +/- 0.28558
Q3_K17.2487 +/- 0.2766817.2950 +/- 0.27994
Q4_016.1358 +/- 0.25091-
Q4_K16.4583 +/- 0.2645316.2688 +/- 0.26216
Q4_015.9068 +/- 0.25545-
Q5_K15.7547 +/- 0.2520716.0190 +/- 0.25782
Q6_K15.8166 +/- 0.2535915.7357 +/- 0.25210
Q8_015.7972 +/- 0.25384-
F1615.8098 +/- 0.25403-

The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).

Others

For Hugging Face version, please see: https://huggingface.co/hfl/chinese-alpaca-2-1.3b

Please refer to https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/ for more details.

hfl/chinese-alpaca-2-1.3b-gguf · CoolFace