Downloads · 30 days
1
10% of all-time downloads
Mellum2-12B-post-post-train
mamoeed/Mellum2-12B-post-post-train
Mellum2-12B-post-post-train is a machine learning model from mamoeed. 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.
An experimental SFT and DPO fine-tune of JetBrains/Mellum2-12B-A2.5B-Thinking using a multi-GPU setup. This model was trained to test distributed training pipelines and data filtering techniques on small datasets. We…
All-time downloads
10
Public
Repo size
48.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors48.6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 22, 2026
- Updated
- Jun 23, 2026
- SHA
- 673f97d6
Base models
Model card
From the Hugging Face model README
Mellum2-12B-SFT-DPO-Experiment
An experimental SFT and DPO fine-tune of JetBrains/Mellum2-12B-A2.5B-Thinking using a multi-GPU setup. This model was trained to test distributed training pipelines and data filtering techniques on small datasets. We release 2 model checkpoints. A SFT only trained version and a DPO (with SFT) version.
Pipeline Details
- SFT Data: 3,000 decontaminated medium/hard samples from
nvidia/OpenCodeReasoning. - DPO Data: 2,439 sandbox-validated pairs from
allenai/Dolci-Think-RL-7B-Completions-DPO. - Hardware: 4x NVIDIA A100 (80GB) utilizing PyTorch FSDP full sharding.
- Precision: BF16
Results & Limitations
When tested against LiveCodeBench v6, the model's Pass@1 score dropped from 0.30 (base) to 0.19. The model appears to have overfitted to the specific reasoning trace formatting of the training data, which introduced syntax styling changes that impacted the evaluation suite.
This model checkpoint is uploaded for infrastructure validation and reproducibility analysis.
- License
- apache-2.0
- Languages
- en
- Created
- Jun 22, 2026
- Updated
- Jun 23, 2026