Model Type |
| ||||||||||||
Use Cases |
| ||||||||||||
Supported Languages |
| ||||||||||||
Training Details |
|
LLM Name | Phi 2 Ov Quantized |
Repository ๐ค | https://huggingface.co/Intel/phi-2-ov-quantized |
Required VRAM | 1.9 GB |
Updated | 2025-02-10 |
Maintainer | Intel |
Model Type | phi |
Model Files | |
Supported Languages | en |
Model Architecture | PhiForCausalLM |
License | mit |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.37.0 |
Tokenizer Class | CodeGenTokenizer |
Vocabulary Size | 51200 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Phi 2 Quantized | 11 | 159 | 1 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi1.5 Quantized 2 | 2K / GB | 5 | 0 |
Merlin1.4 | 2K / 5.6 GB | 101 | 0 |
Merlin1.5 | 2K / 5.6 GB | 102 | 0 |
Merlin1.2 | 2K / 5.6 GB | 88 | 0 |
Merlin1.3 | 2K / 5.6 GB | 93 | 0 |
Phi Bode 2 Ultraalpaca | 2K / 5.6 GB | 452 | 2 |
Tinyllama Quant | 2K / 0.8 GB | 4 | 1 |
Phi1.5 Update 4 | 2K / GB | 6 | 0 |
Phi 2 Fp8 | 2K / 3.3 GB | 89 | 0 |
Phi 2 Fp8 | 2K / 3.3 GB | 81 | 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