Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Conversational Custom code Endpoints compatible Instruct Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/JulienNawak/orpo_phi
Orpo Phi Benchmarks
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)
Orpo Phi Parameters and Internals
| LLM Name | Orpo Phi |
| Repository 🤗 | https://huggingface.co/JulienNawak/orpo_phi |
| Model Size | 2.1b |
| Required VRAM | 7.7 GB |
| Updated | 2024-12-22 |
| Maintainer | JulienNawak |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 32013 |
| Torch Data Type | float32 |
Best Alternatives to Orpo Phi
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi3 Mental Health | 4K / 2.7 GB | 9 | 2 |
| Quantized Phi 3 Mini 4K | 4K / 2.3 GB | 10 | 1 |
| ...Mini 128K Instruct 4bit 64rank | 128K / 2.4 GB | 13 | 0 |
| ... 3 Mini 128K Instruct Bnb 4bit | 128K / 2.3 GB | 27 | 1 |
| ...3 Mini 4K Instruct 4bit 64rank | 4K / 2.4 GB | 19 | 0 |
| Phi 3 Mini 4K Instruct Q4 | 4K / 2.3 GB | 17 | 0 |
| ...hi 3 Mini 4K Instruct Bnb 4bit | 4K / 2.3 GB | 24 | 3 |
| ...hi 3 Mini 4K Instruct Bnb 4bit | 4K / 2.3 GB | 12 | 0 |
Rank the Orpo Phi 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217