Model Card on HF 🤗: https://huggingface.co/cepiloth/ko-llama2-13b-finetune-ex
Ko Llama2 13B Finetune Ex 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)
Ko Llama2 13B Finetune Ex Parameters and Internals
| LLM Name | Ko Llama2 13B Finetune Ex |
| Repository 🤗 | https://huggingface.co/cepiloth/ko-llama2-13b-finetune-ex |
| Model Size | 13b |
| Required VRAM | 26 GB |
| Updated | 2025-05-07 |
| Maintainer | cepiloth |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Ko Llama2 13B Finetune Ex
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Small Tiny V1 | 0K / 0.1 GB | 5 | 0 |
| ALMA 13B R | 0K / 26 GB | 4139 | 81 |
| Llava V1.5 13B S2 Lora | 0K / 0.1 GB | 4 | 2 |
| Llama 2 13B Chat Hf GPT 4 80K | 0K / 26 GB | 10 | 0 |
| ...ama2 13B No Robots Alpaca Lora | 0K / 4 GB | 7 | 10 |
| Ko En Llama2 13B Finetune Ex | 0K / 26 GB | 1409 | 0 |
| Ko En Llama2 13B Finetune | 0K / 26 GB | 1414 | 0 |
| Llava Chart 13b Lora | 0K / 0.1 GB | 4 | 2 |
| ChartLlama 13B | 0K / 0.1 GB | 174 | 19 |
| Leyley 13B Lora | 0K / 4 GB | 4 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than cepiloth/ko-llama2-13b-finetune-ex .
Rank the Ko Llama2 13B Finetune Ex 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? 47060 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227