Downloads · 30 days
4
1% of all-time downloads
SkeptiSTEM-4B-v2-stageR1-merged-16bit
HallD/SkeptiSTEM-4B-v2-stageR1-merged-16bit
SkeptiSTEM-4B-v2-stageR1-merged-16bit is a machine learning model from HallD. 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 is the merged 16-bit checkpoint for SkeptiSTEM-4B-v2 after Stage R1 STEM SFT.
All-time downloads
440
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025
- SHA
- 2f34b751
Base models
Model card
From the Hugging Face model README
SkeptiSTEM-4B-v2 (stageR1) - Merged 16-bit
This is the merged 16-bit checkpoint for SkeptiSTEM-4B-v2 after Stage R1 STEM SFT.
See HallD/SkeptiSTEM-4B-v2-stageR1-lora for the LoRA adapter and training details.
Usage
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name="HallD/SkeptiSTEM-4B-v2-stageR1-merged-16bit",
max_seq_length=4096,
load_in_4bit=True,
)
FastLanguageModel.for_inference(model)
- Type
- qwen3
- License
- apache-2.0
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025