Downloads · 30 days
10
31% of all-time downloads
ScaleSeek-Qwen3.5-9B-SFT
Allenda/ScaleSeek-Qwen3.5-9B-SFT
ScaleSeek-Qwen3.5-9B-SFT is a machine learning model from Allenda. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Cold-start SFT checkpoint (1725 verified multi-hop trajectories, teacher Qwen3.6-35B-A3B).
All-time downloads
32
Public
Parameters
9.4B
37.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors37.6 GB · 100%
At a glance
- Model type
- qwen3_5
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- 0de134cf
Model card
From the Hugging Face model README
ScaleSeek-Qwen3.5-9B-SFT
Cold-start SFT checkpoint (1725 verified multi-hop trajectories, teacher Qwen3.6-35B-A3B).
Base model: Qwen/Qwen3.5-9B. See DATA_PROVENANCE.md for the
training-set checksum.
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("Allenda/ScaleSeek-Qwen3.5-9B-SFT", trust_remote_code=True)
t = AutoTokenizer.from_pretrained("Allenda/ScaleSeek-Qwen3.5-9B-SFT", trust_remote_code=True)
- Type
- qwen3_5
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026