Hugging Face's logo

JosephusCheung
/
GuanacoOnConsumerHardware

Text Generation
Transformers
llama
text-generation-inference
Inference Endpoints
Model card Files
JosephusCheung commited on
Commit
7166e5b
•
1 Parent(s): 2083dca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -2,10 +2,9 @@
2
  license: gpl-3.0
3
  ---
4
 
5
- Free T4 Colab demo:
6
-
7
- [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ESkKNHGdoocsz1F-Eiwx-9L-Ft3rYdfl#scrollTo=zLORi5OcPcIJ)
8
 
 
9
 
10
  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.
11
 
 
2
  license: gpl-3.0
3
  ---
4
 
5
+ Try Multimodal version with Colab Free T4 demo:
 
 
6
 
7
+ [![Open In Colab](hhttps://huggingface.co/JosephusCheung/GuanacoVQAOnConsumerHardware)
8
 
9
  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.
10