JosephusCheung
/

GuanacoOnConsumerHardware

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions

JosephusCheung commited on May 12, 2023

Commit

fc2dc9c

•

1 Parent(s): 7e39dfd

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -4,7 +4,8 @@ license: gpl-3.0
 Try Multimodal version with Colab Free T4 demo:
-![Open In Colab](hhttps://huggingface.co/JosephusCheung/GuanacoVQAOnConsumerHardware)
 This repository is for Guanaco model with 4-bit quantized weights. The model benefits from two novel techniques introduced by GPTQ: quantizing columns in order of decreasing activation size and performing sequential quantization within a single Transformer block. These innovations enable compact, consumer-level multilingual models to function effectively.

 Try Multimodal version with Colab Free T4 demo:
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://huggingface.co/JosephusCheung/GuanacoVQAOnConsumerHardware)
 This repository is for Guanaco model with 4-bit quantized weights. The model benefits from two novel techniques introduced by GPTQ: quantizing columns in order of decreasing activation size and performing sequential quantization within a single Transformer block. These innovations enable compact, consumer-level multilingual models to function effectively.