本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 開放權重模型自訂
<a name="model-customize-open-weight"></a>

本節會逐步引導您開始使用開放權重模型自訂程序。

**Topics**
+ [自訂支援的模型](#model-customize-open-weight-supported-models)
+ [先決條件](model-customize-open-weight-prereq.md)
+ [在 UI 中建立用於模型自訂的資產](model-customize-open-weight-create-assets-ui.md)
+ [AI 模型自訂任務提交](model-customize-open-weight-job.md)
+ [模型評估任務提交](model-customize-open-weight-evaluation.md)
+ [模型部署](model-customize-open-weight-deployment.md)
+ [範例資料集和評估者](model-customize-open-weight-samples.md)

## 自訂支援的模型
<a name="model-customize-open-weight-supported-models"></a>

下表顯示您可以自訂的基本模型。


| 模型提供者 | 模型 | 模型 ID | SFT (LORA) | DPO (LORA) | RLAIF (LORA) | RLVR (LORA) | 
| --- | --- | --- | --- | --- | --- | --- | 
| 阿里巴巴 | Qwen2.5 指示 7B | huggingface-llm-qwen2-5-7b-instruct | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen2.5 指示 14B | huggingface-llm-qwen2-5-14b-instruct | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen2.5 指示 32B | huggingface-llm-qwen2-5-32b-instruct | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen2.5 指示 72B | huggingface-llm-qwen2-5-72b-instruct | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 0.6B | huggingface-reasoning-qwen3-06b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 1.7B | huggingface-reasoning-qwen3-1-7b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 4B | huggingface-reasoning-qwen3-4b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 8B | huggingface-reasoning-qwen3-8b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 14B | huggingface-reasoning-qwen3-14b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3 32B | huggingface-reasoning-qwen3-32b | ✓ | ✓ | ✓ | ✓ | 
| 阿里巴巴 | Qwen3.5 4B | huggingface-vlm-qwen3-5-4b | ✓ |  | ✓ | ✓ | 
| 阿里巴巴 | Qwen3.5 9B | huggingface-vlm-qwen3-5-9b | ✓ |  | ✓ | ✓ | 
| 阿里巴巴 | Qwen3.5 27B | huggingface-vlm-qwen3-5-27b | ✓ |  | ✓ | ✓ | 
| 阿里巴巴 | Qwen3.6 27B | huggingface-vlm-qwen3-6-27b | ✓ |  | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Llama 8B | deepseek-llm-r1-distill-llama-8b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Llama 70B | deepseek-llm-r1-distill-llama-70b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Qwen 1.5B | deepseek-llm-r1-distill-qwen-1-5b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Qwen 7B | deepseek-llm-r1-distill-qwen-7b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Qwen 14B | deepseek-llm-r1-distill-qwen-14b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 停用 Qwen 32B | deepseek-llm-r1-distill-qwen-32b | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.1 指示 8B | meta-textgeneration-llama-3-1-8b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.2 指示 1B | meta-textgeneration-llama-3-2-1b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.2 指示 3B | meta-textgeneration-llama-3-2-3b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Meta Llama 3.3 指示 70B | meta-textgeneration-llama-3-3-70b-instruct | ✓ | ✓ | ✓ | ✓ | 
| OpenAI | GPT OSS 20B | openai-reasoning-gpt-oss-20b | ✓ | ✓ | ✓ | ✓ | 
| OpenAI | GPT OSS 120B | openai-reasoning-gpt-oss-120b | ✓ | ✓ | ✓ | ✓ |