Autotrain compatible Code Cognitivecomputations/dolphin-... Conversational Custom code En Lxuechen/phi-2-dpo Moe Phi-msft Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/phixtral-2x2_8
Phixtral 2x2 8 Benchmarks
MMLU Pro: 17.23
GPQA: 2.01
MUSR: 7.71
BBH: 28.5
IFEval: 34.31 vs 88 (so35)-61%
MATH Lvl 5: 3.55
LLME Score: 0.18587
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)
Phixtral 2x2 8 Parameters and Internals
| Model Type |
| ||||||||||||
| Use Cases |
| ||||||||||||
| Additional Notes |
| ||||||||||||
| Supported Languages |
| ||||||||||||
| Training Details |
| ||||||||||||
| Input Output |
|
| LLM Name | Phixtral 2x2 8 |
| Repository 🤗 | https://huggingface.co/mlabonne/phixtral-2x2_8 |
| Model Size | 4.5b |
| Required VRAM | 8.9 GB |
| Updated | 2025-09-14 |
| Maintainer | mlabonne |
| Model Type | phi-msft |
| Model Files | |
| Supported Languages | en |
| Model Architecture | PhiForCausalLM |
| License | mit |
| Model Max Length | 2048 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Best Alternatives to Phixtral 2x2 8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Samantha Phixtral 2x2 8 | 0K / 8.9 GB | 3 | 1 |
| Phi 2 MoE Test | 0K / 8.9 GB | 3 | 1 |
| Phixtral 4x2 8odd | 0K / 8.9 GB | 4 | 3 |
Rank the Phixtral 2x2 8 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? 51368 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124