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
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...128K Instruct HQQ 2bit Smashed | — | 128K / 1.4 GB | 24 | 0 |
...28K Instruct Ov Fp16 Int4 Asym | — | 128K / 2.5 GB | 76 | 0 |
...m 128K Instruct 3.0bpw H6 EXL2 | — | 128K / 5.6 GB | 7 | 0 |
...m 128K Instruct 5.0bpw H6 EXL2 | — | 128K / 8.9 GB | 15 | 0 |
...m 128K Instruct 6.0bpw H6 EXL2 | — | 128K / 10.7 GB | 4 | 3 |
...m 128K Instruct 8.0bpw H8 EXL2 | — | 128K / 13.4 GB | 20 | 4 |
...dium 128K Instruct 8 0bpw EXL2 | — | 128K / 13.4 GB | 6 | 1 |
Phi 3 Mini 4K Instruct Fp16 | — | 4K / GB | 8 | 1 |
...i 4K Instruct HQQ 1bit Smashed | — | 4K / 0.9 GB | 65 | 0 |
...Instruct V0.3 HQQ 1bit Smashed | — | 4K / 0.9 GB | 8 | 0 |
LLM Name | Microsoft Phi 3 Mini 128K Instruct HQQ 4bit Smashed |
Repository | Open on ๐ค |
Base Model(s) | |
Required VRAM | 2.3 GB |
Updated | 2024-07-07 |
Maintainer | PrunaAI |
Model Type | phi3 |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Phi3ForCausalLM |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.40.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 32064 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |
Embedding Dropout | 0 |