Model Type |
| ||||||||||||||||
Use Cases |
| ||||||||||||||||
Additional Notes | The model employs state-of-the-art training techniques and a curated dataset to deliver enhanced performance across a wide range of tasks. | ||||||||||||||||
Training Details |
|
LLM Name | L3 Aethora 15B V2 EXL2 6.0bpw |
Repository ๐ค | https://huggingface.co/bullerwins/L3-Aethora-15B-V2-exl2_6.0bpw |
Base Model(s) | |
Model Size | 15b |
Required VRAM | 11.9 GB |
Updated | 2024-11-13 |
Maintainer | bullerwins |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | exl2 |
Model Architecture | LlamaForCausalLM |
License | cc-by-sa-4.0 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.40.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
L3 Aethora 15B V2 EXL2 8.0bpw | 8K / 12.4 GB | 11 | 1 |
L3 Aethora 15B V2 EXL2 4.0bpw | 8K / 8.4 GB | 10 | 1 |
L3 Aethora 15B V2 EXL2 5.0bpw | 8K / 10.2 GB | 7 | 1 |
L3 Aethora 15B V2 | 8K / 30.1 GB | 29 | 39 |
OpenCrystal 15B L3 V3 | 8K / 30 GB | 92 | 8 |
OpenCrystal L3 15B V2.1 | 8K / 30 GB | 8 | 5 |
OpenCrystal 15B L3 V2 | 8K / 30 GB | 13 | 4 |
Meta Llama 3 15B Instruct | 8K / 23.9 GB | 10 | 1 |
Llama 3 15B Instruct Ft V2 AWQ | 8K / 9.4 GB | 5 | 0 |
Llama 3 15B Instruct Ft V2 | 8K / 30.1 GB | 11 | 4 |
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