LLM Name | Phi 3 Mini 4K Instruct Fp8 |
Repository ๐ค | https://huggingface.co/unrahul/Phi-3-mini-4k-instruct-fp8 |
Required VRAM | 4.3 GB |
Updated | 2025-01-27 |
Maintainer | unrahul |
Model Type | phi3 |
Instruction-Based | Yes |
Model Files | |
Model Architecture | Phi3ForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 32064 |
Torch Data Type | float32 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Phi 3 Mini 4K Instruct Fp16 | 3 | 508 | 0 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi 3.5 Mini Instruct Onnx | 128K / GB | 393 | 25 |
Phi 3.5 Mini Instruct Onnx Web | 128K / GB | 608 | 13 |
Phi 3 Mini 128K Instruct Onnx | 128K / GB | 417 | 185 |
...Medium 128K Instruct Onnx Cuda | 128K / GB | 110 | 23 |
... Medium 128K Instruct Onnx Cpu | 128K / GB | 91 | 11 |
...i 3 Mini 128K Instruct Ov Int4 | 128K / 2 GB | 5 | 0 |
...3 Mini 128K Instruct Asym Int4 | 128K / 2.5 GB | 127 | 0 |
...3 Mini 128K Instruct Asym Int4 | 128K / 2.5 GB | 122 | 0 |
...um 128K Instruct Onnx Directml | 128K / GB | 42 | 5 |
Model1 | 128K / 0.8 GB | 20 | 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