Upload README.md
Browse files
README.md
CHANGED
|
@@ -18,16 +18,18 @@ tags:
|
|
| 18 |
- qwen2
|
| 19 |
---
|
| 20 |
|
|
|
|
|
|
|
| 21 |
# tool_call_validator_zh
|
| 22 |
|
| 23 |
-
> LoRA fine-tune of Qwen2.5-3B-Instruct
|
| 24 |
> Traditional Chinese tool-call validator (guardrail) — LoRA fine-tune of Qwen2.5-3B-Instruct
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
## 中文說明
|
| 29 |
|
| 30 |
-
本模型是針對 **Tool Call Validation** 場景微調的繁體中文模型。基於 [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) 用 LoRA 訓練，能夠：
|
| 31 |
|
| 32 |
1. 讀取使用者請求（user prompt）與多個候選工具的 description
|
| 33 |
2. 透過語意比對選出最適合的工具，或在無合適工具時拒絕匹配
|
|
|
|
| 18 |
- qwen2
|
| 19 |
---
|
| 20 |
|
| 21 |
+
|
| 22 |
+
|
| 23 |
# tool_call_validator_zh
|
| 24 |
|
| 25 |
+
> 中文 (繁體) Tool Call 驗證 / Guardrail 模型 · LoRA fine-tune of Qwen2.5-3B-Instruct
|
| 26 |
> Traditional Chinese tool-call validator (guardrail) — LoRA fine-tune of Qwen2.5-3B-Instruct
|
| 27 |
|
| 28 |
---
|
| 29 |
|
| 30 |
## 中文說明
|
| 31 |
|
| 32 |
+
本模型是針對 **Tool Call Validation / Guardrail** 場景微調的繁體中文模型。基於 [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) 用 LoRA 訓練，能夠：
|
| 33 |
|
| 34 |
1. 讀取使用者請求（user prompt）與多個候選工具的 description
|
| 35 |
2. 透過語意比對選出最適合的工具，或在無合適工具時拒絕匹配
|