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 |
---|---|---|---|---|
... 3 Mini 128K Instruct Bnb 4bit | — | 128K / 2.3 GB | 127 | 1 |
...Mini 128K Instruct 4bit 64rank | — | 128K / 2.4 GB | 955 | 0 |
Phi 3 Mini 4K Instruct Q4 | — | 4K / 2.3 GB | 127 | 0 |
...hi 3 Mini 4K Instruct Bnb 4bit | — | 4K / 2.3 GB | 6 | 0 |
...3 Mini 4K Instruct 4bit 64rank | — | 4K / 2.4 GB | 44 | 0 |
Quantized Phi 3 Mini 4K | — | 4K / 2.3 GB | 13 | 1 |
Phi3 Mental Health | — | 4K / 2.7 GB | 731 | 1 |
Orpo Phi | — | 4K / 7.7 GB | 16 | 0 |
LLM Name | Phi 3 Mini 4K Instruct Bnb 4bit |
Repository | Open on ๐ค |
Model Name | Phi-3-mini-4k-instruct |
Model Creator | Microsoft |
Base Model(s) | |
Model Size | 2.1b |
Required VRAM | 2.3 GB |
Updated | 2024-07-07 |
Maintainer | leliuga |
Model Type | phi3 |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Phi3ForCausalLM |
License | other |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.40.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|placeholder6|> |
Vocabulary Size | 32064 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |
Embedding Dropout | 0 |