Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

# Kustomisasi model bobot terbuka
<a name="model-customize-open-weight"></a>

Bagian ini memandu Anda melalui proses untuk memulai dengan kustomisasi model bobot terbuka.

**Topics**
+ [Model yang didukung untuk kustomisasi](#model-customize-open-weight-supported-models)
+ [Prasyarat](model-customize-open-weight-prereq.md)
+ [Membuat aset untuk kustomisasi model di UI](model-customize-open-weight-create-assets-ui.md)
+ [Pengajuan pekerjaan kustomisasi model AI](model-customize-open-weight-job.md)
+ [Pengajuan pekerjaan evaluasi model](model-customize-open-weight-evaluation.md)
+ [Deployment model](model-customize-open-weight-deployment.md)
+ [Contoh kumpulan data dan evaluator](model-customize-open-weight-samples.md)

## Model yang didukung untuk kustomisasi
<a name="model-customize-open-weight-supported-models"></a>

Tabel berikut menunjukkan model dasar yang dapat Anda sesuaikan.


| Penyedia Model | Model | ID Model | SFT (LORA) | DPO (LORA) | RLAIF (LORA) | RLVR (LORA) | 
| --- | --- | --- | --- | --- | --- | --- | 
| Alibaba | Qwen2.5 Instruksikan 7B | huggingface-llm-qwen2-5-7b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen2.5 Instruksikan 14B | huggingface-llm-qwen2-5-14b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen2.5 Instruksikan 32B | huggingface-llm-qwen2-5-32b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen2.5 Instruksikan 72B | huggingface-llm-qwen2-5-72b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen3 0.6B | huggingface-reasoning-qwen3-06b | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen3 1.7B | huggingface-reasoning-qwen3-1-7b | ✓ | ✓ | ✓ | ✓ | 
| Alibaba | Qwen3 4B | 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 R1 Suling Llama 8B | deepseek-llm-r1-distill-llama-8b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 Suling Llama 70B | deepseek-llm-r1-distill-llama-70b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 Suling Qwen 1.5B | deepseek-llm-r1-distill-qwen-1-5b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 Suling Qwen 7B | deepseek-llm-r1-distill-qwen-7b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 Suling Qwen 14B | deepseek-llm-r1-distill-qwen-14b | ✓ | ✓ | ✓ | ✓ | 
| DeepSeek | DeepSeek R1 Suling Qwen 32B | deepseek-llm-r1-distill-qwen-32b | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.1 Instruksi 8B | meta-textgeneration-llama-3-1-8b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.2 Instruksi 1B | meta-textgeneration-llama-3-2-1b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Llama 3.2 Instruksi 3B | meta-textgeneration-llama-3-2-3b-instruct | ✓ | ✓ | ✓ | ✓ | 
| Meta | Meta Llama 3.3 Instruksi 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 | ✓ | ✓ | ✓ | ✓ |