Downloads · 30 days
8
4% of all-time downloads
Qwen3-1.7B-OPD-step120
boyanbiji/Qwen3-1.7B-OPD-step120
Qwen3-1.7B-OPD-step120 is a text generation model from boyanbiji. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
On-Policy Distillation (OPD) checkpoint at global step 120.
All-time downloads
207
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026
- SHA
- fd9b2ed9
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-1.7B-OPD-step120
On-Policy Distillation (OPD) checkpoint at global step 120.
- Student / base model:
Qwen/Qwen3-1.7B-Base - Teacher:
Qwen/Qwen3-8B(non-thinking mode) - Training data:
zwhe99/DeepMath-103K - Precision: bfloat16
- Max response length: 8192 tokens
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "boyanbiji/Qwen3-1.7B-OPD-step120"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")
Evaluation sampling parameters used in our experiments:
temperature=0.7, top_p=0.8, top_k=20, max_len=16384, n=32.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026