Model Card on HF 🤗: https://huggingface.co/AlexCuadron/dpo_roleplay
DPO Roleplay 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)
DPO Roleplay Parameters and Internals
| LLM Name | DPO Roleplay |
| Repository 🤗 | https://huggingface.co/AlexCuadron/dpo_roleplay |
| Model Size | 12.2b |
| Required VRAM | 24.5 GB |
| Updated | 2025-08-28 |
| Maintainer | AlexCuadron |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to DPO Roleplay
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...aptain Eris Violet GRPO V0.420 | 1000K / 24.5 GB | 55 | 23 |
| Kalypso | 1000K / 24.5 GB | 300 | 15 |
| ...ish Mistral Nemo Instruct 2407 | 1000K / 24.5 GB | 77 | 2 |
| Funny Nemo Embedding Testing | 1000K / 24.5 GB | 18 | 0 |
| Tess Embed Fix Maybe | 1000K / 24.5 GB | 13 | 0 |
| Violet Twilight V0.2 | 1000K / 24.5 GB | 301 | 40 |
| 12BTRU | 1000K / 24.5 GB | 21 | 0 |
| A Strange Nemo Model | 1000K / 24.5 GB | 12 | 0 |
| Another Strange Nemo Model | 1000K / 24.5 GB | 9 | 0 |
| Mistral Nemo Kurdish | 1000K / 24.5 GB | 3 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than AlexCuadron/dpo_roleplay .
Rank the DPO Roleplay 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? 50958 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124