기계 번역으로 제공되는 번역입니다. 제공된 번역과 원본 영어의 내용이 상충하는 경우에는 영어 버전이 우선합니다.
개방형 가중치 모델 사용자 지정
이 섹션에서는 개방형 가중치 모델 사용자 지정을 시작하는 프로세스를 안내합니다.
지원되는 모델 및 사용자 지정 유형
다음 표에는 LoRA 또는 전체 미세 조정(FFT)을 사용하는 SFT, DPO, RLVR 및 RLAIF를 포함하여 각 모델에 대해 지원되는 미세 조정 레시피가 나와 있습니다.
| 제공업체 | 모델 | 모델 ID | SFT(LoRA) | SFT(FFT) | DPO(LoRA) | DPO(FFT) | RLVR(LoRA) | RLVR(FFT) | RLAIF(LoRA) | RLAIF(FFT) |
|---|---|---|---|---|---|---|---|---|---|---|
| 알리바바 | Qwen3.6 27B | huggingface-vlm-qwen3-6-27b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3.5 27B | huggingface-vlm-qwen3-5-27b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3.5 9B | huggingface-vlm-qwen3-5-9b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3.5 4B | huggingface-vlm-qwen3-5-4b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3 32B | huggingface-reasoning-qwen3-32b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3 14B | huggingface-reasoning-qwen3-14b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3 8B | huggingface-reasoning-qwen3-8b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3 4B | huggingface-reasoning-qwen3-4b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen3 1.7B | huggingface-reasoning-qwen3-1-7b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| 알리바바 | Qwen3 0.6B | huggingface-reasoning-qwen3-06b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen2.5 명령 72B | huggingface-llm-qwen2-5-72b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | |||
| 알리바바 | Qwen2.5 명령 32B | huggingface-llm-qwen2-5-32b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen2.5 명령 14B | huggingface-llm-qwen2-5-14b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| 알리바바 | Qwen2.5 명령 7B | huggingface-llm-qwen2-5-7b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | R1 Distill Qwen 32B | deepseek-llm-r1-distill-qwen-32b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | R1 Distill Qwen 14B | deepseek-llm-r1-distill-qwen-14b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | R1 Distill Qwen 7B | deepseek-llm-r1-distill-qwen-7b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| DeepSeek | R1 Distill Qwen 1.5B | deepseek-llm-r1-distill-qwen-1-5b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| DeepSeek | R1 Distill Llama 70B | deepseek-llm-r1-distill-llama-70b | ✓ | ✓ | ✓ | ✓ | ✓ | |||
| DeepSeek | R1 Distill Llama 8B | deepseek-llm-r1-distill-llama-8b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Gemma 4 31B | huggingface-vlm-gemma-4-31b-it | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Gemma 4 26B A4B | huggingface-vlm-gemma-4-26b-a4b-it | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Gemma 4 E4B | huggingface-vlm-gemma-4-e4b-it | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Meta | Llama 3.3 명령 70B | meta-textgeneration-llama-3-3-70b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Meta | Llama 3.2 명령 3B | meta-textgeneration-llama-3-2-3b-instruct | ✓ | ✓ | ✓ | ✓ | ||||
| Meta | Llama 3.2 명령 1B | meta-textgeneration-llama-3-2-1b-instruct | ✓ | ✓ | ✓ | ✓ | ||||
| Meta | Llama 3.1 명령 8B | meta-textgeneration-llama-3-1-8b-instruct | ✓ | ✓ | ✓ | ✓ | ||||
| NVIDIA | Nemotron 3 Super 120B(A12B) | huggingface-llm-nvidia-nemotron-3-super-120b-a12b-bf16 | ✓ | ✓ | ✓ | |||||
| NVIDIA | Nemotron 3 Nano 30B(A3B) | huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ||
| OpenAI | GPT OSS 120B | openai-reasoning-gpt-oss-120b | ✓ | ✓ | ✓ | ✓ | ||||
| OpenAI | GPT OSS 20B | openai-reasoning-gpt-oss-20b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
