| | --- |
| | title: Ollama DeepSeek-R1 + Qwen3-VL |
| | emoji: 🤖 |
| | colorFrom: blue |
| | colorTo: purple |
| | sdk: docker |
| | pinned: false |
| | app_port: 7860 |
| | --- |
| | |
| | # Ollama — DeepSeek-R1 + Qwen3-VL |
| |
|
| | Serwer Ollama z dwoma modelami, chroniony kluczem API. |
| |
|
| | | Model | Typ | Rozmiar | |
| | |-------|-----|---------| |
| | | `deepseek-r1:latest` | LLM reasoning | ~4.7GB | |
| | | `qwen3-vl:latest` | Vision-Language | ~5.4GB | |
| |
|
| | ## Autoryzacja |
| |
|
| | Każde żądanie wymaga nagłówka: |
| | ``` |
| | Authorization: Bearer connectkey |
| | ``` |
| |
|
| | ## Endpoints |
| |
|
| | | Method | Path | Opis | |
| | |--------|------|------| |
| | | `GET` | `/api/version` | Wersja Ollama | |
| | | `GET` | `/api/tags` | Lista modeli | |
| | | `POST` | `/api/generate` | Generowanie (stream) | |
| | | `POST` | `/api/chat` | Chat (stream) | |
| | | `POST` | `/api/embeddings` | Embeddingi | |
| |
|
| | ## Przykład |
| |
|
| | ```bash |
| | curl https://<user>-<space>.hf.space/api/chat \ |
| | -H "Authorization: Bearer connectkey" \ |
| | -d '{"model":"deepseek-r1:latest","messages":[{"role":"user","content":"Hello!"}]}' |
| | ``` |
| |
|
