Arxiv:2412.08905 4-bit 4bit Autotrain compatible Base model:microsoft/phi-4 Base model:quantized:microsoft... Bitsandbytes Chat Code Conversational En Endpoints compatible Llama Math Phi Phi4 Quantized Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit
Phi 4 Unsloth Bnb 4bit Benchmarks
MMLU Pro: 47.62
GPQA: 11.52
MUSR: 8.76
BBH: 53.84
IFEval: 67.94 vs 88 (so35)-22.8%
MATH Lvl 5: 20.02
LLME Score: 0.53735
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phi 4 Unsloth Bnb 4bit Parameters and Internals
| LLM Name | Phi 4 Unsloth Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit |
| Base Model(s) | |
| Model Size | 8.5b |
| Required VRAM | 10.4 GB |
| Updated | 2025-01-15 |
| Maintainer | unsloth |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Quantized Models of the Phi 4 Unsloth Bnb 4bit
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Phi 4 COT | 0 | 35 | 29 GB |
| ...ocalAI Functioncall Phi 4 V0.3 | 0 | 15 | 29 GB |
| Phi 4 RP Lora Model | 3 | 0 | 0 GB |
Rank the Phi 4 Unsloth Bnb 4bit Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 41418 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227