Text Generation
Safetensors
English
Chinese
Min Nan Chinese
gemma4
elderly-care
companion
taiwanese
hokkien
voice-assistant
unsloth
qLoRA
conversational
Instructions to use Rayantion26/JINGSI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Studio
How to use Rayantion26/JINGSI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Rayantion26/JINGSI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Rayantion26/JINGSI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Rayantion26/JINGSI to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Rayantion26/JINGSI", max_seq_length=2048, )
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -212,11 +212,20 @@ curl -X POST http://localhost:8000/v1/chat/completions \
|
|
| 212 |
|
| 213 |
## 📊 Test Results / 測試結果
|
| 214 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 215 |
| Category / 類別 | Tests / 測試數 | Pass Rate / 通過率 |
|
| 216 |
|----------|-------|-----------|
|
| 217 |
-
| Identity / 身份 |
|
| 218 |
-
| Emotion (EN) / 情緒(英文) |
|
| 219 |
-
| Emotion (ZH) / 情緒(中文) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
| 台語 (Taiwanese) | 16 | 100% |
|
| 221 |
| Refusal / 拒絕 | 18 | 100% |
|
| 222 |
| Wisdom / 智慧 | 26 | 100% |
|
|
|
|
| 212 |
|
| 213 |
## 📊 Test Results / 測試結果
|
| 214 |
|
| 215 |
+
**English:** 220/220 (100%) tests passed via vLLM with 4-bit bitsandbytes quantization in a Podman container. Tests cover identity, emotion (EN/ZH/台語), refusal, injection, wisdom — all through the production vLLM deployment.
|
| 216 |
+
|
| 217 |
+
**繁體中文:** 220/220(100%)測試通過,使用 vLLM 4-bit bitsandbytes 量化於 Podman 容器中。測試涵蓋身份、情緒(英文/中文/台語)、拒絕、注入攻擊、智慧 — 全部通過生產環境 vLLM 部署。
|
| 218 |
+
|
| 219 |
| Category / 類別 | Tests / 測試數 | Pass Rate / 通過率 |
|
| 220 |
|----------|-------|-----------|
|
| 221 |
+
| Identity / 身份 | 40 | 100% |
|
| 222 |
+
| Emotion (EN) / 情緒(英文) | 40 | 100% |
|
| 223 |
+
| Emotion (ZH) / 情緒(中文) | 40 | 100% |
|
| 224 |
+
| Refusal / 拒絕 | 40 | 100% |
|
| 225 |
+
| 台語 | 20 | 100% |
|
| 226 |
+
| Injection / 注入攻擊 | 20 | 100% |
|
| 227 |
+
| Wisdom / 智慧 | 20 | 100% |
|
| 228 |
+
| **Total / 總計** | **220** | **100%** |
|
| 229 |
| 台語 (Taiwanese) | 16 | 100% |
|
| 230 |
| Refusal / 拒絕 | 18 | 100% |
|
| 231 |
| Wisdom / 智慧 | 26 | 100% |
|