Matthew Douglas
mdouglas
AI & ML interests
LLMs, quantization, NLP, embeddings, hardware, DevEx
Recent Activity
liked
a model
about 1 month ago
microsoft/phi-4
liked
a model
about 2 months ago
answerdotai/ModernBERT-base
liked
a model
5 months ago
meta-llama/Llama-3.2-1B
Organizations
mdouglas's activity
update the config.json and the weights
1
#1 opened 6 months ago
by
Rudra-ai
4 bit and 8 bit bnb quants only generate empty strings or one token repeated endlessly
2
#32 opened 7 months ago
by
nicorinn-google
4bit-quantized gemma-2-27b-it generates only pad tokens, like '<pad><pad><pad><pad><pad><pad><pad><pad><pad>'.
6
#29 opened 7 months ago
by
kshinoda
Update bitsandbytes examples
1
#33 opened 6 months ago
by
mdouglas
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6400f6cc2b67d27affcfdb93/WA6FEZy_YaZPGhIWj2zda.jpeg)
Update `license`
#1 opened 7 months ago
by
alvarobartt
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/BHso-wSWpR9b8b8CKvodC.jpeg)
Adding `safetensors` variant of this model
#1 opened about 1 year ago
by
SFconvertbot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635fd4cc14657fb8cff2a081/GDkyDwAcuqDBpaOvQgJuq.png)