Arxiv:1910.09700 8-bit Autotrain compatible Bitsandbytes Endpoints compatible Phi Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/marcosciala/pastanoodles_dpo_quant
Pastanoodles DPO Quant 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)
Pastanoodles DPO Quant Parameters and Internals
| LLM Name | Pastanoodles DPO Quant |
| Repository 🤗 | https://huggingface.co/marcosciala/pastanoodles_dpo_quant |
| Model Size | 2.8b |
| Required VRAM | 3 GB |
| Updated | 2025-02-22 |
| Maintainer | marcosciala |
| Model Type | phi |
| Model Files | |
| Model Architecture | PhiForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | CodeGenTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
Best Alternatives to Pastanoodles DPO Quant
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MFANN3bv0.24 | 128K / 11.1 GB | 16 | 0 |
| MFANN3b | 128K / 11.1 GB | 66 | 0 |
| MFANN Phigments Slerp V3.2 | 128K / 5.6 GB | 33 | 0 |
| MFANN3bv1.4 | 128K / 11.1 GB | 22 | 0 |
| MFANN3bv1.3 | 128K / 11.1 GB | 25 | 0 |
| MFANN3bv0.23 | 128K / 11.1 GB | 36 | 0 |
| MFANN3bv1.1 | 128K / 11.1 GB | 13 | 0 |
| MFANN3b SFT | 128K / 5.6 GB | 65 | 0 |
| MFANN3b Rebase | 128K / 11.1 GB | 13 | 0 |
| MFANN3bv1.2 | 126K / 11.1 GB | 39 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than marcosciala/pastanoodles_dpo_quant .
Rank the Pastanoodles DPO Quant 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227