Downloads · 30 days
15
4% of all-time downloads
OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF
ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF
OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF is a text generation model from ermiaazarkhalili. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as cc-by-4.0.
GGUF quantizations of a LoRA fine-tune of nvidia/OpenMath-Nemotron-1.5B, trained with GRPO (reinforcement learning) on AI-MO/NuminaMath-CoT.
All-time downloads
416
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- cc-by-4.0
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Aug 4, 2026
- SHA
- ef52b17b
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF
GGUF quantizations of a LoRA fine-tune of nvidia/OpenMath-Nemotron-1.5B, trained with GRPO (reinforcement learning) on AI-MO/NuminaMath-CoT.
Quantized from ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K. See that repository for the full-precision weights.
| Base model | nvidia/OpenMath-Nemotron-1.5B |
| Training data | AI-MO/NuminaMath-CoT |
| Method | LoRA GRPO (reinforcement learning) via Unsloth + TRL |
| License | cc-by-4.0 (inherited from the base model) |
Available quantizations
| File | Size |
|---|---|
openmath-nemotron-1.5b-grpo-numinamath-10k.q4_k_m.gguf | 986 MB |
openmath-nemotron-1.5b-grpo-numinamath-10k.q5_k_m.gguf | 1.13 GB |
openmath-nemotron-1.5b-grpo-numinamath-10k.q8_0.gguf | 1.65 GB |
Usage
llama.cpp
huggingface-cli download ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF openmath-nemotron-1.5b-grpo-numinamath-10k.q4_k_m.gguf --local-dir .
llama-cli -m openmath-nemotron-1.5b-grpo-numinamath-10k.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256
Ollama
echo 'FROM ./openmath-nemotron-1.5b-grpo-numinamath-10k.q4_k_m.gguf' > Modelfile
ollama create openmath-nemotron-1.5b-grpo-numinamath-10k-gguf -f Modelfile
ollama run openmath-nemotron-1.5b-grpo-numinamath-10k-gguf
Limitations
- No benchmark evaluation has been run on this checkpoint. The only reported numbers are training-loss observations.
- Inherits the biases, knowledge cutoff and failure modes of the base model.
- Fine-tuned on a single instruction-following dataset; behaviour outside that distribution is untested.
- LoRA adapters were merged into the base weights, so the merged model cannot be detached from this fine-tune.
Reproducing
Produced by an Unsloth + TRL LoRA training pipeline, executed non-interactively with papermill on a SLURM H100 partition.
Card generated from the training run's own configuration and logs by
scripts/generate_hub_model_card.py.
- Task
- Text Generation
- Library
- gguf
- License
- cc-by-4.0
- Created
- Jul 4, 2026
- Updated
- Aug 4, 2026