Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Instruct Ko Llama Lora Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch1
SKY Ko Llama3.2 3B Lora Epoch1 Benchmarks
MMLU Pro: 22.27
GPQA: 5.59
MUSR: 5.96
BBH: 20.81
IFEval: 53.31 vs 88 (so35)-39.4%
MATH Lvl 5: 14.58
LLME Score: 0.27528
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)
SKY Ko Llama3.2 3B Lora Epoch1 Parameters and Internals
| LLM Name | SKY Ko Llama3.2 3B Lora Epoch1 |
| Repository 🤗 | https://huggingface.co/SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch1 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-04-12 |
| Maintainer | SkyOrbis |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ko |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
Best Alternatives to SKY Ko Llama3.2 3B Lora Epoch1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1682574 | 1489 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 468 | 11 |
| Orpheus 3B 0.1 Pretrained | 128K / 6.6 GB | 10964 | 0 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 11 | 2 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 213683 | 66 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| Llama 3.2 3B Bespoke Thought | 128K / 6.4 GB | 448 | 3 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 40 | 1 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 48 | 0 |
| Llama 3.2 3B ToxicKod | 128K / 6.4 GB | 9 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch1 .
Rank the SKY Ko Llama3.2 3B Lora Epoch1 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227