Downloads · 30 days
8
38% of all-time downloads
cd3arg-Qwen2.5-1.5B-Instruct-R1-SFT
SkillFactory/cd3arg-Qwen2.5-1.5B-Instruct-R1-SFT
cd3arg-Qwen2.5-1.5B-Instruct-R1-SFT is a machine learning model from SkillFactory. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Exported from LLaMA-Factory - Intended for Countdown 3-args (baseline)
All-time downloads
21
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025
- SHA
- d37aeee7
Model card
From the Hugging Face model README
M-R1 distilled baseline (cd3args only)
- Exported from LLaMA-Factory
- Intended for Countdown 3-args (baseline)
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained('TAUR-dev/M-R1_distilled_baseline_cd3args_only')
model = AutoModelForCausalLM.from_pretrained('TAUR-dev/M-R1_distilled_baseline_cd3args_only', torch_dtype='auto')
- Type
- qwen2
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025