LLM Name | Falcon 7B Instruct Bnb 8bit |
Repository | Open on ๐ค |
Model Size | 7b |
Required VRAM | 7.2 GB |
Updated | 2024-07-27 |
Maintainer | alokabhishek |
Model Type | falcon |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 8bit |
Model Architecture | FalconForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.39.3 |
Is Biased | 0 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 65024 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
Falcon 7B Instruct Bnb 4bit | 0.2 | 2K / 4 GB | 15 | 1 |
...n 7B Instruct Bnb 8bit Smashed | 0.2 | 0K / 7.2 GB | 7 | 0 |
... Openassistant Toxicity Reduce | 0.2 | 2K / 30.4 GB | 13 | 0 |
New Falcon | 0.2 | 2K / 4.3 GB | 15 | 1 |
Claire 7B 0.1 Instruct | 0.2 | 2K / 7.2 GB | 12 | 1 |
New Falcon | — | 2K / 4.3 GB | 0 | 0 |
Falcon 7B Instruct | 0.3 | 0K / 14.4 GB | 461376 | 889 |
Falcon 7B Instruct Quant | 0.2 | 0K / 4 GB | 37 | 0 |
Falcon 7B Instruct Ft | 0.2 | 0K / 13.9 GB | 8 | 0 |
Falcon 7B IT Technical Support | 0.2 | 0K / 13.8 GB | 8 | 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