Downloads · 30 days
10
16% of all-time downloads
qwen3-1.7b-self-aligned
ITBill/qwen3-1.7b-self-aligned
qwen3-1.7b-self-aligned is a text generation model from ITBill. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter trained for final instruction-following SFT in the self-alignment reproduction pipeline.
All-time downloads
61
Public
Repo size
81.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors69.8 MB · 86%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Apr 13, 2026
- Updated
- Apr 13, 2026
- SHA
- ca10bf7f
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-1.7B Self-Aligned LoRA
LoRA adapter trained for final instruction-following SFT in the self-alignment reproduction pipeline.
Base Model
Qwen/Qwen3-1.7B
Local Artifact Source
- folder:
adapter-261949 - repo id:
ITBill/qwen3-1.7b-self-aligned
Training Summary
- global step: 3
- train loss: 2.41523806254069
- eval loss: 2.3819782733917236
Files
adapter_model.safetensors: LoRA weightsadapter_config.json: PEFT adapter configtokenizer.jsonandtokenizer_config.json: tokenizer assets used for the runtraining_summary.json: exported local training summary
- Task
- Text Generation
- Library
- peft
- Created
- Apr 13, 2026
- Updated
- Apr 13, 2026