Base model:adapter:n-bot-int/o... Base model:n-bot-int/openrp3b-... Conversational Dataset:flammenai/character-ro... Dataset:kingbri/pippa-sharegpt Dataset:openerotica/mixed-rp En Llama Lora Peft Region:us Roleplay Safetensors Trl Uncensored Unsloth
Model Card on HF 🤗: https://huggingface.co/N-Bot-Int/OpenElla3-Llama3.2B
OpenElla3 Llama3.2B 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)
OpenElla3 Llama3.2B Parameters and Internals
| LLM Name | OpenElla3 Llama3.2B |
| Repository 🤗 | https://huggingface.co/N-Bot-Int/OpenElla3-Llama3.2B |
| Base Model(s) | |
| Required VRAM | 0 GB |
| Updated | 2025-05-10 |
| Maintainer | N-Bot-Int |
| Model Files | |
| Supported Languages | en |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|gate_proj|o_proj|k_proj|v_proj|up_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.3 |
| R Param | 8 |
Best Alternatives to OpenElla3 Llama3.2B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Distil Longformer Base 4096 | 4K / 0.4 GB | 7 | 0 |
| Daedalus 1 | 1K / GB | 17 | 1 |
| Tiny Random Detr | 1K / 0.2 GB | 5 | 0 |
| Opengpt2 Pytorch Backward | 1K / 6 GB | 62 | 1 |
| Opengpt2 Pytorch Forward | 1K / 6 GB | 5 | 1 |
| Finsent Transformer | 0.5K / 0.4 GB | 5 | 1 |
| Simbert Chinese Tiny | 0.5K / 0 GB | 15 | 0 |
| Bert Chinese L 12 H 768 A 12 | 0.5K / 0.4 GB | 7 | 1 |
| Simbert Chinese Base | 0.5K / 0.4 GB | 10 | 0 |
| All MiniLM L12 V2 | 0.5K / GB | 885 | 3 |
Rank the OpenElla3 Llama3.2B 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? 47217 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227