Le traduzioni sono generate tramite traduzione automatica. In caso di conflitto tra il contenuto di una traduzione e la versione originale in Inglese, quest'ultima prevarrà.
Personalizzazione del modello a peso aperto
Questa sezione illustra il processo per iniziare con la personalizzazione del modello a peso aperto.
Argomenti
Modelli e tipi di personalizzazione supportati
La tabella seguente mostra le ricette di ottimizzazione supportate per ciascun modello, tra cui SFT, DPO, RLVR e RLAIF con o regolazione completa (FFT). LoRA
| Provider | Modello | ID modello | SFT () LoRA | SFT (FFT) | DPO () LoRA | DPO (FFT) | RLVR () LoRA | RLVR (FFT) | RLAIF () LoRA | RLAIF (FFT) |
|---|---|---|---|---|---|---|---|---|---|---|
| Alibaba | Qwen3.6 27B | huggingface-vlm-qwen3-6-27b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3.5 27B | huggingface-vlm-qwen3-5-27b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3.5 9B | huggingface-vlm-qwen3-5-9b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3.5 4B | huggingface-vlm-qwen3-5-4b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 32B | huggingface-reasoning-qwen3-32b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen 3 14B | huggingface-reasoning-qwen3-14b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen 3 8B | huggingface-reasoning-qwen3-8b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 4B | huggingface-reasoning-qwen3-4b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen 3 1,7 B | huggingface-reasoning-qwen3-1-7b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| Alibaba | Qwen3 0,6 B | huggingface-reasoning-qwen3-06b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Istruisci 72B | huggingface-llm-qwen2-5-72b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | |||
| Alibaba | Qwen2.5 Istruisci 32B | huggingface-llm-qwen2-5-32b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Istruisci 14B | huggingface-llm-qwen2-5-14b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Istruisci 7B | huggingface-llm-qwen2-5-7b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | Distillatore E1 Qwen 32B | deepseek-llm-r1-distill-qwen-32b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | Distillatore R1 Qwen 14B | deepseek-llm-r1-distill-qwen-14b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| DeepSeek | Distillatore R1 Qwen 7B | deepseek-llm-r1-distill-qwen-7b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| DeepSeek | Distillatore R1 Qwen 1.5B | deepseek-llm-r1-distill-qwen-1-5b | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | |
| DeepSeek | Distillatore R1 Llama 70B | deepseek-llm-r1-distill-llama-70b | ✓ | ✓ | ✓ | ✓ | ✓ | |||
| DeepSeek | Distillatore R1 Lama 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 Instruct 70B | meta-textgeneration-llama-3-3-70b-instruct | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Meta | Llama 3.2 Istruisci 3B | meta-textgeneration-llama-3-2-3b-instruct | ✓ | ✓ | ✓ | ✓ | ||||
| Meta | Llama 3.2 Istruisci 1B | meta-textgeneration-llama-3-2-1b-instruct | ✓ | ✓ | ✓ | ✓ | ||||
| Meta | Llama 3.1 Istruisci 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 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
