Merged Model Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Region:us Safetensors Sharded Stablelm Tensorflow
Model Card on HF 🤗: https://huggingface.co/AlexVal/dpo_model
DPO Model 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 Model Parameters and Internals
| LLM Name | DPO Model |
| Repository 🤗 | https://huggingface.co/AlexVal/dpo_model |
| Merged Model | Yes |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2025-08-29 |
| Maintainer | AlexVal |
| Model Type | stablelm |
| Model Files | |
| Model Architecture | StableLmForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 50278 |
| Torch Data Type | float16 |
Best Alternatives to DPO Model
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Adolf Hitler | 4K / 10.6 GB | 19 | 0 |
| Mcqa Model Full Only Mcqa | 4K / 5.6 GB | 5 | 0 |
| Mcqa Model Full New | 4K / 5.6 GB | 5 | 0 |
| Mcqa Model Full | 4K / 5.6 GB | 5 | 0 |
| Mcqa Model | 4K / 5.6 GB | 5 | 0 |
| Sft Model | 4K / 5.6 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than AlexVal/dpo_model .
Rank the DPO Model 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? 51550 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124