8-bit 8bit Autotrain compatible Bitsandbytes Endpoints compatible Phi Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/syr99/bnb_dpo_8bit
Bnb DPO 8bit 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)
Bnb DPO 8bit Parameters and Internals
| LLM Name | Bnb DPO 8bit |
| Repository 🤗 | https://huggingface.co/syr99/bnb_dpo_8bit |
| Model Size | 2.8b |
| Required VRAM | 3 GB |
| Updated | 2025-02-05 |
| Maintainer | syr99 |
| Model Type | phi |
| Model Files | |
| Quantization Type | 8bit |
| 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 | float16 |
Best Alternatives to Bnb DPO 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 2 4bit 64rank | 2K / 5.6 GB | 153 | 0 |
| Phi 2 Nf4 Fp16 Upscaled | 2K / 5.6 GB | 26 | 0 |
| MFANN3bv0.24 | 128K / 11.1 GB | 5 | 0 |
| MFANN3b | 128K / 11.1 GB | 116 | 0 |
| MFANN3bv1.3 | 128K / 11.1 GB | 13 | 0 |
| MFANN3bv1.1 | 128K / 11.1 GB | 16 | 0 |
| MFANN3bv0.23 | 128K / 11.1 GB | 6 | 0 |
| MFANN3b SFT | 128K / 5.6 GB | 169 | 0 |
| MFANN3b Rebase | 128K / 11.1 GB | 10 | 0 |
| MFANN3bv1.2 | 126K / 11.1 GB | 32 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than syr99/bnb_dpo_8bit .
Rank the Bnb DPO 8bit 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227