Downloads · 30 days
10
12% of all-time downloads
LoRA-trained-smollm2
susuahi/LoRA-trained-smollm2
LoRA-trained-smollm2 is a machine learning model from susuahi. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
81
Public
Parameters
1.8B
13.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
BF161.8B · 100%
Model card
From the Hugging Face model README
LoRA-trained-smollm2
SmolLM2 监督微调（SFT）对话模型
训练曲线
训练指标
- Train Loss: 1.2008
- Validation Loss: 1.2428
- Total Steps: 1000
训练参数
- Learning Rate: 5e-05
- Batch Size: 4
使用方法
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("susuahi/LoRA-trained-smollm2")
tokenizer = AutoTokenizer.from_pretrained("susuahi/LoRA-trained-smollm2")
- Type
- qwen2
- Created
- Mar 26, 2026
- Updated
- Mar 26, 2026