LLM Name | Alfred 40B 1023 AWQ |
Repository ๐ค | https://huggingface.co/TheBloke/alfred-40B-1023-AWQ |
Model Name | Alfred 40B 1023 |
Model Creator | LightOn AI |
Base Model(s) | |
Model Size | 40b |
Required VRAM | 23.3 GB |
Updated | 2024-09-18 |
Maintainer | TheBloke |
Model Type | RefinedWeb |
Model Files | |
Supported Languages | en fr de es it |
AWQ Quantization | Yes |
Quantization Type | awq |
Model Architecture | RWForCausalLM |
License | apache-2.0 |
Model Max Length | 8192 |
Transformers Version | 4.35.0 |
Is Biased | 0 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 65024 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...alcon 40B Instruct W4 G128 AWQ | 0K / 22.3 GB | 10 | 2 |
Falcon 40B 8bit | 0K / 41.8 GB | 6 | 1 |
Falcon 40B Instruct 8bit | 0K / 41.8 GB | 10 | 6 |
Alfred 40B 1023 | 0K / 83.6 GB | 1462 | 45 |
Vulture 40B | 0K / 81.8 GB | 1429 | 7 |
Alfred 40B 1023 GPTQ | 0K / 22.5 GB | 9 | 3 |
FalconLite | 0K / 22.3 GB | 124 | 172 |
...m Oasst1 En 2048 Falcon 40B V2 | 0K / 83.6 GB | 3011 | 18 |
Docsgpt 40B Falcon | 0K / 82.5 GB | 23 | 13 |
Alfred 40B 0723 | 0K / 83.6 GB | 9 | 45 |
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