Arxiv:2203.05482 Ad æternum Amazing Autotrain compatible Base model:harbingerx/zeitgeis... Base model:hastagaras/l3.2-jam... Base model:lunahr/thea-rp-3b-2... Base model:merge:harbingerx/ze... Base model:merge:hastagaras/l3... Base model:merge:lunahr/thea-r... Conversational Cute Dataset:kingnish/reasoning-bas... Dataset:lunahr/thea-name-overr... Dataset:replete-ai/apocrypha De En Endpoints compatible Es Fr It I❤️🔥jajuka Ja Ko Llama Lovely Merge Mergekit Model-index Mt Not-for-all-audiences Pt Region:us Roleplay Rp Ru Safetensors Sharded Storyteller Tensorflow Text2text Textgeneration Zh
Model Card on HF 🤗: https://huggingface.co/RezVortex/Jajuka-3b
Jajuka 3B Benchmarks
MMLU Pro: 23.75
GPQA: 2.13
MUSR: 6.59
BBH: 23.2
IFEval: 69.25 vs 88 (so35)-21.3%
MATH Lvl 5: 15.94
LLME Score: 0.31082
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)
Jajuka 3B Parameters and Internals
| LLM Name | Jajuka 3B |
| Repository 🤗 | https://huggingface.co/RezVortex/Jajuka-3b |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.4 GB |
| Updated | 2025-03-05 |
| Maintainer | RezVortex |
| Model Type | llama |
| Model Files | |
| Supported Languages | en de es pt zh fr it ja ko ru mt |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Jajuka 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ISA 03 Mini 3B Hybrid Preview | 256K / 6.5 GB | 1468 | 3 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1505928 | 1377 |
| Llama 3.2 3B | 128K / 6.5 GB | 655983 | 552 |
| Cogito V1 Preview Llama 3B | 128K / 7.2 GB | 7531 | 92 |
| Hermes 3 Llama 3.2 3B | 128K / 6.5 GB | 11658 | 151 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 717 | 11 |
| Orpheus 3B 0.1 Ft | 128K / 6.6 GB | 8509 | 2 |
| Calme 3.1 Llamaloi 3B | 128K / 10.6 GB | 3044 | 1 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 15 | 2 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than RezVortex/Jajuka-3b .
Rank the Jajuka 3B 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? 46678 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227