LLM Name | Microsoft Phi 3 Medium 4K Instruct 8 Bit Gptq |
Repository ๐ค | https://huggingface.co/SotiriosKastanas/microsoft-Phi-3-medium-4k-instruct-8-bit-gptq |
Model Size | 3.9b |
Required VRAM | 14.6 GB |
Updated | 2025-02-13 |
Maintainer | SotiriosKastanas |
Model Type | phi3 |
Instruction-Based | Yes |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | Phi3ForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 32064 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...edium 128K Instruct GPTQ 8 Bit | 128K / 14.6 GB | 41 | 0 |
...um 128K Instruct GPTQ 8 Bit C4 | 128K / 14.6 GB | 8 | 0 |
...hi 3 Medium 128K Instruct 8bit | 128K / 14.9 GB | 19 | 2 |
Phi 3 Medium 4K Instruct 8bit | 4K / 14.9 GB | 11 | 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