Autotrain compatible Base model:finetune:unsloth/ll... Base model:unsloth/llama-3.2-3... Dpo En Endpoints compatible Llama Pytorch Region:us Sharded Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/shayanfirouzian/Llama-3.2-3B-DPO-SocialReasoning
Llama 3.2 3B DPO SocialReasoning 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)
Llama 3.2 3B DPO SocialReasoning Parameters and Internals
| LLM Name | Llama 3.2 3B DPO SocialReasoning |
| Repository 🤗 | https://huggingface.co/shayanfirouzian/Llama-3.2-3B-DPO-SocialReasoning |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-06-10 |
| Maintainer | shayanfirouzian |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.51.3 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama 3.2 3B DPO SocialReasoning
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 594 | 3 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1541897 | 1507 |
| Llama 3.2 3B | 128K / 6.5 GB | 280627 | 574 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 44844 | 160 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 1085 | 13 |
| Cogito V1 Preview Llama 3B | 128K / 7.2 GB | 2763 | 95 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 22539 | 3 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 3628 | 1 |
| Orpheus 3B 0.1 Pretrained | 128K / 6.6 GB | 10490 | 0 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 212732 | 66 |
Note: green Score (e.g. "73.2") means that the model is better than shayanfirouzian/Llama-3.2-3B-DPO-SocialReasoning .
Rank the Llama 3.2 3B DPO SocialReasoning 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? 48075 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124