Model Card on HF 🤗: https://huggingface.co/syr99/qlora4b_dpo
Qlora4b DPO 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)
Qlora4b DPO Parameters and Internals
| LLM Name | Qlora4b DPO |
| Repository 🤗 | https://huggingface.co/syr99/qlora4b_dpo |
| Model Size | 1.6b |
| Required VRAM | 2.5 GB |
| Updated | 2025-05-26 |
| Maintainer | syr99 |
| Model Type | phi |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | <pad><pad><pad> |
| Vocabulary Size | 50296 |
| Torch Data Type | float32 |
Best Alternatives to Qlora4b DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qlora4b Phi | 2K / 2.5 GB | 14 | 0 |
| ...reamtobenlpsama Mcqa Quantized | 2K / 1.8 GB | 6 | 0 |
| TeachersHateChatbotsMCQ Mini | 2K / 2.4 GB | 6 | 0 |
| Qlora4b DPO | 2K / 2.5 GB | 6 | 0 |
| Qlora4b Phi | 2K / 2.5 GB | 6 | 0 |
| Phi2 Spelling | 2K / 1.8 GB | 6 | 0 |
| Phi 2 Voicechange | 2K / 2.5 GB | 7 | 0 |
| Phi2 Changevoice | 2K / 2.4 GB | 6 | 0 |
| Phi 2 Maths | 2K / 1.9 GB | 6 | 2 |
| Phi2 Ner V1 | 2K / 1.9 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than syr99/qlora4b_dpo .
Rank the Qlora4b DPO 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124