Hugging Face's logo

ISTA-DASLab
/
Meta-Llama-3-8B-AQLM-PV-2Bit-1x16

Text Generation
Transformers
Safetensors
llama
facebook
meta
llama-3
conversational
text-generation-inference
Inference Endpoints
aqlm
Model card Files Community
justheuristic commited on
Commit
d07dd43
•
1 Parent(s): ab6d880

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ Note that a large portion of this model are the 16-bit embeddings/logits matrice
18
  | Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
19
  |------------|-------------|----------------|----------------|--------------------------------------------------------------------------|
20
  | meta-llama/Meta-Llama-3-8B (this) | 1x16g8 | 6.99 | 4.1 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-2Bit-1x16) |
21
- | meta-llama/Meta-Llama-3-8B | 1x16g16 | 6.99 | 3.9 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-1Bit-1x16) |
22
  | meta-llama/Meta-Llama-3-70B | 1x16g8 | 4.57 | 21.9 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-2Bit-1x16)|
23
 
24
  The 1x16g16 (1-bit) models are on the way, as soon as we update the inference lib with their respective kernels.
 
18
  | Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
19
  |------------|-------------|----------------|----------------|--------------------------------------------------------------------------|
20
  | meta-llama/Meta-Llama-3-8B (this) | 1x16g8 | 6.99 | 4.1 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-2Bit-1x16) |
21
+ | meta-llama/Meta-Llama-3-8B | 1x16g16 | 9.43 | 3.9 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-8B-AQLM-PV-1Bit-1x16) |
22
  | meta-llama/Meta-Llama-3-70B | 1x16g8 | 4.57 | 21.9 | [Link](https://huggingface.co/ISTA-DASLab/Meta-Llama-3-70B-AQLM-PV-2Bit-1x16)|
23
 
24
  The 1x16g16 (1-bit) models are on the way, as soon as we update the inference lib with their respective kernels.