LLM Name | Tiiuae Falcon 40B Instruct 4 Bit Bnb |
Repository ๐ค | https://huggingface.co/SotiriosKastanas/tiiuae-falcon-40b-instruct-4-bit-bnb |
Model Size | 40b |
Required VRAM | 23.9 GB |
Updated | 2025-02-01 |
Maintainer | SotiriosKastanas |
Model Type | falcon |
Instruction-Based | Yes |
Model Files | |
Model Architecture | FalconForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.42.0.dev0 |
Is Biased | 0 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 65024 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...Falcon 40B Instruct 4 Bit Gptq | 0 | 5 | 22 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Falcon 40B Instruct | 0K / 83.6 GB | 134526 | 1174 |
...Falcon 40B Instruct 4 Bit Gptq | 2K / 22.3 GB | 5 | 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