Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Instruct Ko Llama Lora Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/SkyOrbis/SKY-Ko-Llama3.2-1B-lora-epoch3
SKY Ko Llama3.2 1B Lora Epoch3 Benchmarks
MMLU Pro: 3.1
GPQA: 0.22
MUSR: 2.07
BBH: 5.49
IFEval: 32.47 vs 88 (so35)-63.1%
MATH Lvl 5: 0.45
LLME Score: 0.28569
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 1B Lora Epoch3 Parameters and Internals
| LLM Name | SKY Ko Llama3.2 1B Lora Epoch3 |
| Repository 🤗 | https://huggingface.co/SkyOrbis/SKY-Ko-Llama3.2-1B-lora-epoch3 |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2.5 GB |
| Updated | 2024-12-26 |
| Maintainer | SkyOrbis |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ko |
| Model Architecture | LlamaForCausalLM |
| License | llama3 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to SKY Ko Llama3.2 1B Lora Epoch3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 1719867 | 661 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 71400 | 46 |
| FastLlama 3.2 1B Instruct | 128K / 4.9 GB | 1306 | 10 |
| Llama 3.2 SUN HDIC 1B Instruct | 128K / 3 GB | 128 | 0 |
| Vikhr Llama 3.2 1B Instruct | 128K / 2.5 GB | 5332 | 37 |
| Explore Llama 3.2 1B Inst V1.1 | 128K / 2.5 GB | 401 | 0 |
| Llama3.2 Typhoon2 1B Instruct | 128K / 2.5 GB | 189 | 2 |
| Llama 3.2 SUN 2.5B Chat | 128K / 4.9 GB | 398 | 1 |
| FuseChat Llama 3.2 1B Instruct | 128K / 2.5 GB | 434 | 4 |
| ... 1B Instruct Medmcqa Zh Linear | 128K / 4.9 GB | 321 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SkyOrbis/SKY-Ko-Llama3.2-1B-lora-epoch3 .
Rank the SKY Ko Llama3.2 1B Lora Epoch3 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? 40303 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227