Model Type |
| |||||||||
Training Details |
| |||||||||
Input Output |
|
LLM Name | Tiiuae Falcon 7B Instruct Bnb 8bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/tiiuae-falcon-7b-instruct-bnb-8bit-smashed |
Model Size | 7b |
Required VRAM | 7.2 GB |
Updated | 2025-01-23 |
Maintainer | PrunaAI |
Model Type | falcon |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 8bit |
Model Architecture | FalconForCausalLM |
Transformers Version | 4.37.1 |
Is Biased | 0 |
Vocabulary Size | 65024 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Falcon 7B Instruct Bnb 8bit | 2K / 7.2 GB | 7 | 1 |
Falcon 7B Instruct Bnb 4bit | 2K / 4 GB | 8 | 1 |
... Openassistant Toxicity Reduce | 2K / 30.4 GB | 19 | 0 |
New Falcon | 2K / 4.3 GB | 10 | 1 |
Claire 7B 0.1 Instruct | 2K / 7.2 GB | 126 | 1 |
New Falcon | 2K / 4.3 GB | 0 | 0 |
Falcon 7B Instruct | 0K / 14.4 GB | 157318 | 938 |
Falcon 7B Instruct Quant | 0K / 4 GB | 236 | 0 |
Falcon 7B Instruct Ft | 0K / 13.9 GB | 17 | 0 |
Falcon 7B IT Technical Support | 0K / 13.8 GB | 17 | 1 |
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