LLM Name | Aya 23 8B 4bit |
Repository ๐ค | https://huggingface.co/mlx-community/aya-23-8B-4bit |
Base Model(s) | |
Model Size | 8b |
Required VRAM | 4.5 GB |
Updated | 2024-10-12 |
Maintainer | mlx-community |
Model Type | cohere |
Model Files | |
Supported Languages | en fr de es it pt ja ko zh ar el fa pl id cs he hi nl ro ru tr uk vi |
Quantization Type | 4bit |
Model Architecture | CohereForCausalLM |
License | cc-by-nc-4.0 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.40.0.dev0 |
Tokenizer Class | CohereTokenizer |
Padding Token | <PAD> |
Vocabulary Size | 256000 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...4ai Command R 08 2024 Bnb 4bit | 128K / 19.9 GB | 1003 | 6 |
Aya 23 8B 3.0bpw H6 EXL2 | 8K / 5.9 GB | 45 | 0 |
...ereForAI Aya 23 8B 6 0bpw EXL2 | 8K / 9.2 GB | 10 | 2 |
Aya 23 8B 6.0bpw H6 EXL2 | 8K / 8.9 GB | 16 | 1 |
...ereForAI Aya 23 8B 8 0bpw EXL2 | 8K / 10.2 GB | 12 | 1 |
Aya 23 8B 8bit | 8K / 8.5 GB | 11 | 1 |
...ereForAI Aya 23 8B 2 2bpw EXL2 | 8K / 5.1 GB | 12 | 0 |
...reForAI Aya 23 8B 3 75bpw EXL2 | 8K / 6.7 GB | 10 | 0 |
Aya 23 8B 5.0bpw H6 EXL2 | 8K / 7.9 GB | 6 | 1 |
Aya 23 8B 4.0bpw H6 EXL2 | 8K / 6.9 GB | 6 | 0 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐