Model Card on HF 🤗: https://huggingface.co/nakhyeon/polyglot-ko-12b-qlora
Polyglot Ko 12B Qlora 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)
Polyglot Ko 12B Qlora Parameters and Internals
| LLM Name | Polyglot Ko 12B Qlora |
| Repository 🤗 | https://huggingface.co/nakhyeon/polyglot-ko-12b-qlora |
| Model Size | 12b |
| Required VRAM | 25.9 GB |
| Updated | 2025-02-22 |
| Maintainer | nakhyeon |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | mit |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | dense_h_to_4h|embed_out|dense|query_key_value|dense_4h_to_h |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 8 |
Best Alternatives to Polyglot Ko 12B Qlora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Ultra Instruct 12B | 0K / 24.5 GB | 22 | 4 |
| Orthrus 12B V0.8 | 0K / 24.5 GB | 16 | 4 |
| WorldBuilder 12B | 0K / 24.5 GB | 5 | 0 |
| CleverBoi Nemo 12B V2 | 0K / 0.2 GB | 566 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than nakhyeon/polyglot-ko-12b-qlora .
Rank the Polyglot Ko 12B Qlora 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227