Welcome Llama 3 - Meta's new open LLM
•
208
Younes Belkada
ybelkada
AI & ML interests
Large Language Models, Quantization, Vision, Multimodality, Diffusion models
Articles
Organizations
Posts
2
Post
Check out quantized weights from ISTA-DAS Lab directly in their organisation page: https://huggingface.co/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
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!
spaces
24
models
137
ybelkada/TinyLlama-1.1B-Chat-v1.0-Q4_0-GGUF
Updated
•
40
ybelkada/test-llava-13b
Image-Text-to-Text
•
Updated
ybelkada/blip-image-captioning-base-football-finetuned
Other
•
Updated
•
315
•
1
ybelkada/falcon-7b-sharded-bf16
Text Generation
•
Updated
•
9.82k
•
19
ybelkada/pix2struct-base-football
Text2Text Generation
•
Updated
•
12
•
1
ybelkada/mistral-7b-instruct-v0.1-sharded
Text Generation
•
Updated
•
21
ybelkada/gpt2-xl-8bit
Text Generation
•
Updated
•
237
ybelkada/stable-diffusion-v1-5
Text-to-Image
•
Updated
•
2
ybelkada/test-automatic-tagging-from-trainer
Updated
•
1
ybelkada/test-automatic-tagging
Text Generation
•
Updated
•
6
datasets
12
ybelkada/model_cards_correct_tag
Viewer
•
Updated
•
7
ybelkada/model-info-library-name
Updated
ybelkada/test-model-info-library-name
Viewer
•
Updated
ybelkada/documentation-images
Viewer
•
Updated
ybelkada/oasst1-tiny-subset
Viewer
•
Updated
•
10
•
2
ybelkada/oasst1
Viewer
•
Updated
•
1
ybelkada/food101-tiny
Viewer
•
Updated
ybelkada/test-onepiece-dataset
Viewer
•
Updated
ybelkada/common_voice_mr_11_0_copy
Viewer
•
Updated
•
74
ybelkada/english_quotes_copy
Viewer
•
Updated
•
777