Downloads · 30 days
8
27% of all-time downloads
ScaleSeek-Qwen3.5-9B-GRPO-step190
Allenda/ScaleSeek-Qwen3.5-9B-GRPO-step190
ScaleSeek-Qwen3.5-9B-GRPO-step190 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.
GRPO checkpoint at step 190, warm-started from the SFT checkpoint above.
All-time downloads
30
Public
Parameters
9.4B
18.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors18.8 GB · 100%
At a glance
- Model type
- qwen3_5
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- c6c2203e
Model card
From the Hugging Face model README
ScaleSeek-Qwen3.5-9B-GRPO-step190
GRPO checkpoint at step 190, warm-started from the SFT checkpoint above.
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-GRPO-step190", trust_remote_code=True)
t = AutoTokenizer.from_pretrained("Allenda/ScaleSeek-Qwen3.5-9B-GRPO-step190", trust_remote_code=True)
- Type
- qwen3_5
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026