Base model:carrotai/llama-3.2-... Base model:finetune:carrotai/l... Conversational Dataset:carrotai/carrot Dataset:carrotai/chat-template En Instruct Ko Llama Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412
Llama 3.2 Rabbit Ko 3B Instruct 2412 Benchmarks
MMLU Pro: 23.71
GPQA: 5.7
MUSR: 6.8
BBH: 20.18
IFEval: 47.82 vs 88 (so35)-45.7%
MATH Lvl 5: 17.6
LLME Score: 0.32353
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 Rabbit Ko 3B Instruct 2412 Parameters and Internals
| LLM Name | Llama 3.2 Rabbit Ko 3B Instruct 2412 |
| Repository 🤗 | https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-03-03 |
| Maintainer | CarrotAI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ko en |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3.2 Rabbit Ko 3B Instruct 2412
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 2566098 | 1140 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 186 | 3 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| ...eflection L3.2 JametMiniMix 3B | 128K / 6.4 GB | 150 | 0 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 109 | 0 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 135 | 0 |
| ...lama 3.2 Rabbit Ko 3B Instruct | 128K / 6.5 GB | 2321 | 8 |
| Orca Mini V9 5 3B Instruct | 128K / 6.5 GB | 101 | 6 |
| Llama 3.2 3B Math Oct | 128K / 6.5 GB | 148 | 10 |
| Eximius Persona 5B | 128K / 11.6 GB | 70 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct-2412 .
Rank the Llama 3.2 Rabbit Ko 3B Instruct 2412 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? 44127 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227