Exaone Verireason Sft Accuracy Medium 1to7 Ratio0.05 Seed2026 is an open-source language model by Jongbin-kr. Features: 7.8b LLM, VRAM: 0.3GB, Instruction-Based, LLM Explorer Score: 0.27.
| LLM Name | Exaone Verireason Sft Accuracy Medium 1to7 Ratio0.05 Seed2026 |
| Repository 🤗 | https://huggingface.co/Jongbin-kr/exaone-verireason-sft_accuracy_medium_1to7_ratio0.05_seed2026 |
| Base Model(s) | |
| Model Size | 7.8b |
| Required VRAM | 0.3 GB |
| Updated | 2026-10-25 |
| Maintainer | Jongbin-kr |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | [PAD] |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | c_proj|out_proj|c_fc_0|q_proj|v_proj|c_fc_1|k_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.05 |
| R Param | 64 |
| Errors | replace |