Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper
• 2601.04890 • Published
• 42
AI & ML interests
None defined yet.
Recent Activity
View all activity
ybelkada
authored a paper about 2 months ago
ybelkada
authored 2 papers 7 months ago
Post
5852
Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!
Contributions are welcome to support more models! 🔥
Contributions are welcome to support more models! 🔥
ybelkada
authored a paper over 1 year ago
Post
5989
Falcon Mamba now available now in llama.cpp !
Check out GGUF files uploaded here: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
Check out GGUF files uploaded here: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
- 3 replies
Post
4160
FalconMamba 7B - a new model from TII (Technology Innovation Institute) is out !
- Blogpost: https://huggingface.co/blog/falconmamba
- Link to collection: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
- Link to playground: tiiuae/falcon-mamba-playground
- Blogpost: https://huggingface.co/blog/falconmamba
- Link to collection: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
- Link to playground: tiiuae/falcon-mamba-playground
ArthurZ
authored a paper almost 2 years ago
Post
Check out quantized weights from ISTA-DAS Lab directly in their organisation page: 
ISTA-DASLab ! With official weights of AQLM (for 2bit quantization) & QMoE (1-bit MoE quantization)
Read more about these techniques below:
AQLM paper: Extreme Compression of Large Language Models via Additive Quantization (2401.06118)
QMoE: QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models (2310.16795)
Some useful links below:
AQLM repo: https://github.com/Vahe1994/AQLM
How to use AQLM & transformers: https://huggingface.co/docs/transformers/quantization#aqlm
How to use AQLM & PEFT: https://huggingface.co/docs/peft/developer_guides/quantization#aqlm-quantizaion
Great work from @BlackSamorez and team !
Read more about these techniques below:
AQLM paper: Extreme Compression of Large Language Models via Additive Quantization (2401.06118)
QMoE: QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models (2310.16795)
Some useful links below:
AQLM repo: https://github.com/Vahe1994/AQLM
How to use AQLM & transformers: https://huggingface.co/docs/transformers/quantization#aqlm
How to use AQLM & PEFT: https://huggingface.co/docs/peft/developer_guides/quantization#aqlm-quantizaion
Great work from @BlackSamorez and team !
Post
mamba is now available in transformers. Thanks to @tridao and @albertgu for this brilliant model! 🚀 and the amazing mamba-ssm kernels powering this!Checkout the collection here:
state-spaces/transformers-compatible-mamba-65e7b40ab87e5297e45ae406
-
- 5 replies
ArthurZ
authored a paper about 2 years ago
Post
Just when I was about to go to bed....... Here we go again
Post
Try out Mixtral 2-bit on a free-tier Google Colab notebook right now!
https://colab.research.google.com/drive/1-xZmBRXT5Fm3Ghn4Mwa2KRypORXb855X?usp=sharing
AQLM method has been recently introduced on transformers main branch
The 2bit model can be found here: BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch
And you can read more about the method here: https://huggingface.co/docs/transformers/main/en/quantization#aqlm
Great work @BlackSamorez and team!
https://colab.research.google.com/drive/1-xZmBRXT5Fm3Ghn4Mwa2KRypORXb855X?usp=sharing
AQLM method has been recently introduced on transformers main branch
The 2bit model can be found here: BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch
And you can read more about the method here: https://huggingface.co/docs/transformers/main/en/quantization#aqlm
Great work @BlackSamorez and team!
-
- 5 replies
ybelkada
authored a paper about 2 years ago
ybelkada
authored a paper over 2 years ago
Rivoks
updated 2 models almost 3 years ago
Rivoks
updated a dataset almost 3 years ago
ybelkada
updated a model almost 3 years ago
Rivoks
updated a model almost 3 years ago