Downloads · 30 days
55
10% of all-time downloads
smolk12_dpo
zariness00/smolk12_dpo
smolk12_dpo is a text generation model from zariness00. Use it when you need the model to write or continue text.
This model is finetuned version of HuggingFaceTB/SmolLM2-360M-Instruct. It has been trained using TRL.
All-time downloads
559
Public
Parameters
362M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Text Generation
- Model type
- llama
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 16, 2026
- SHA
- 4c238535
Try a prompt
Base models
Model card
From the Hugging Face model README
This model is finetuned version of HuggingFaceTB/SmolLM2-360M-Instruct. It has been trained using TRL.
Quick start
Training procedure
The model was trained with DPO
- Task
- Text Generation
- Type
- llama
- Created
- Sep 2, 2026
- Updated
- Sep 16, 2026