Downloads · 30 days
5
9% of all-time downloads
qwen25-3b-full-sft-multihop
Anna4242/qwen25-3b-full-sft-multihop
qwen25-3b-full-sft-multihop is a machine learning model from Anna4242. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model was fine-tuned using SFT on multi-hop tool-use tasks.
All-time downloads
55
Public
Parameters
3.1B
18.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt12.3 GB · 67%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Nov 28, 2025
- Updated
- Nov 28, 2025
- SHA
- 3d700495
Base models
Model card
From the Hugging Face model README
Qwen2.5-3B Full SFT Multi-hop
This model was fine-tuned using SFT on multi-hop tool-use tasks.
Training Details
- Base Model: Qwen/Qwen2.5-3B-Instruct
- Training Method: Supervised Fine-Tuning (SFT)
- Task: Multi-hop tool-use (3-6-9 hop)
- Checkpoint: Step 609
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Anna4242/qwen25-3b-full-sft-multihop")
tokenizer = AutoTokenizer.from_pretrained("Anna4242/qwen25-3b-full-sft-multihop")
- Type
- qwen2
- License
- apache-2.0
- Created
- Nov 28, 2025
- Updated
- Nov 28, 2025