Downloads · 30 days
13
25% of all-time downloads
DylanDeep-Core-8B
dylxnmyl/DylanDeep-Core-8B
DylanDeep-Core-8B is a machine learning model from dylxnmyl. 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 cc-by-nc-nd-4.0.
cd ~/checkpoints/abelcombineddpomerged && cat README.md << 'MODELCARD' --- license: other licensename: cc-by-nc-nd-4.0-with-llama2 licenselink: LICENSE basemodel: GAIR/Abel-7B-002 tags: - math - reasoning - gsm8k - dp…
All-time downloads
52
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- License
- cc-by-nc-nd-4.0
- Model type
- mistral
- Access
- Public
- Created
- Nov 21, 2025
- Updated
- Nov 24, 2025
- SHA
- 3765dcb9
Base models
Datasets
Model card
From the Hugging Face model README
cd ~/checkpoints/abel_combined_dpo_merged && cat > README.md << 'MODELCARD'
license: other license_name: cc-by-nc-nd-4.0-with-llama2 license_link: LICENSE base_model: GAIR/Abel-7B-002 tags:
- math
- reasoning
- gsm8k
- dpo
- rlhf datasets:
- gsm8k metrics:
- accuracy
DylanDeep-Core-8B-DPO
A math reasoning model achieving 84.84% on GSM8K through preference optimization.
Model Details
- Base: Abel-7B-002 (LLaMA-2 architecture)
- Method: SFT + DPO with counterfactual reasoning
- Evaluation: 8-shot majority voting
Performance
| Model | GSM8K Accuracy |
|---|---|
| Abel-7B-002 (base) | 79.08% |
| + SFT | 84.46% |
| + DPO | 84.84% |
Training
Fine-tuned with LoRA adapters using a two-stage approach:
- Supervised fine-tuning on GSM8K training set
- DPO on 3,334 preference pairs with counterfactual probing
Training Code
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("dylxnmyl/DylanDeep-Core-8B-DPO")
tokenizer = AutoTokenizer.from_pretrained("dylxnmyl/DylanDeep-Core-8B-DPO")
License
This model is released under CC BY-NC-ND 4.0 with the following conditions:
Non-commercial use only
No derivatives without permission
Attribution required
Additionally, this model inherits the LLaMA 2 Community License from its base model. Users must comply with both licenses. MODELCARD
- Type
- mistral
- License
- cc-by-nc-nd-4.0
- Languages
- en
- Created
- Nov 21, 2025
- Updated
- Nov 24, 2025