Las traducciones son generadas a través de traducción automática. En caso de conflicto entre la traducción y la version original de inglés, prevalecerá la version en inglés.
Personalización del modelo de peso abierto
En esta sección, se explica el proceso para empezar a personalizar los modelos de peso abierto.
Modelos compatibles para la personalización
En la siguiente tabla se muestran los modelos básicos que se pueden personalizar.
| Proveedor de modelos | Modelo | ID del modelo | SOFT (FLORA) | DPO (LORA) | RLAIF (LORA) | RLVR (LORA) |
|---|---|---|---|---|---|---|
| Alibaba | Qwen2.5 Instruye a 7B | huggingface-llm-qwen2-5-7b-instruct |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Instructa 14B | huggingface-llm-qwen2-5-14b-instruct |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Instructa 32B | huggingface-llm-qwen2-5-32b-instruct |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen2.5 Instrucción 72B | huggingface-llm-qwen2-5-72b-instruct |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 0,6 B | huggingface-reasoning-qwen3-06b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 1,7 B | huggingface-reasoning-qwen3-1-7b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 4G | huggingface-reasoning-qwen3-4b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 8B | huggingface-reasoning-qwen3-8b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 14B | huggingface-reasoning-qwen3-14b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3 32B | huggingface-reasoning-qwen3-32b |
✓ | ✓ | ✓ | ✓ |
| Alibaba | Qwen3.5 4B | huggingface-vlm-qwen3-5-4b |
✓ | ✓ | ✓ | |
| Alibaba | Qwen3.5 9B | huggingface-vlm-qwen3-5-9b |
✓ | ✓ | ✓ | |
| Alibaba | Qwen3.5 27B | huggingface-vlm-qwen3-5-27b |
✓ | ✓ | ✓ | |
| Alibaba | Qwen3.6 27B | huggingface-vlm-qwen3-6-27b |
✓ | ✓ | ✓ | |
| DeepSeek | DeepSeek Llama destiladora R1 8B | deepseek-llm-r1-distill-llama-8b |
✓ | ✓ | ✓ | ✓ |
| DeepSeek | DeepSeek R1 Destila Llama 70B | deepseek-llm-r1-distill-llama-70b |
✓ | ✓ | ✓ | ✓ |
| DeepSeek | DeepSeek Destilador R1 Awen de 1,5 V | deepseek-llm-r1-distill-qwen-1-5b |
✓ | ✓ | ✓ | ✓ |
| DeepSeek | DeepSeek R1 Destila Qwen 7B | deepseek-llm-r1-distill-qwen-7b |
✓ | ✓ | ✓ | ✓ |
| DeepSeek | DeepSeek R1 Destila Qwen 14B | deepseek-llm-r1-distill-qwen-14b |
✓ | ✓ | ✓ | ✓ |
| DeepSeek | DeepSeek R1 Destilador Qwen 32B | deepseek-llm-r1-distill-qwen-32b |
✓ | ✓ | ✓ | ✓ |
| Meta | Llama 3.1 Instruct 8B | meta-textgeneration-llama-3-1-8b-instruct |
✓ | ✓ | ✓ | ✓ |
| Meta | Llama 3.2 Instruct 1B | meta-textgeneration-llama-3-2-1b-instruct |
✓ | ✓ | ✓ | ✓ |
| Meta | Llama 3.2 Instruct 3B | meta-textgeneration-llama-3-2-3b-instruct |
✓ | ✓ | ✓ | ✓ |
| Meta | Meta Llama 3.3 Instruct 70B | meta-textgeneration-llama-3-3-70b-instruct |
✓ | ✓ | ✓ | ✓ |
| OpenAI | TENGO UNA PÉRDIDA DE 200 GB | openai-reasoning-gpt-oss-20b |
✓ | ✓ | ✓ | ✓ |
| OpenAI | GPT BOSS 120 GB | openai-reasoning-gpt-oss-120b |
✓ | ✓ | ✓ | ✓ |