Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Container
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0训练信息
| 参数 | 值 |
|---|---|
| 基座模型 | Qwen2.5-1.5B-Instruct |
| 数据集 | coffee-sft-v5 (3825条) |
| LoRA rank | 16 |
| LoRA alpha | 32 |
| 训练 epoch | 3 |
| Adapter 大小 | 73.9 MB |
| 硬件 | RTX 4060 8GB |
| 训练时长 | ~70 min |
能力评测
| 维度 | 得分 | 说明 |
|---|---|---|
| 咖啡参数 | 10/10 | 🏆 满分 |
| 寒暄社交 | ✅ | 自然对话 |
| 故障排查 | ✅ | 过萃/堵杯/crema |
| 清洁保养 | ✅ | 摩卡壶/意式机/磨豆机 |
| 购买建议 | ✅ | 新手推荐/预算选购 |
| 辟谣知识 | ✅ | 深烘/健康/猫屎咖啡 |
使用方法
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelmodel = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct",torch_dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(model, "ynanxiu/qwen25-15b-coffee-lora-v5")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")# 开始聊天！
相关资源
Model provider
ynanxiu
Model tree
Base
Qwen/Qwen2.5-1.5B-Instruct
Adapter
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information