---

license: llama3.2

base_model:

- meta-llama/Llama-3.2-3B-Instruct

datasets:

- AI-MO/NuminaMath-CoT

library_name: gguf

pipeline_tag: text-generation

tags:

- gguf

- llama.cpp

- quantized

- unsloth

- lora

- trl

- grpo

- rl

---

Llama-3.2-3B-Instruct-GRPO-NuminaMath-10K-GGUF

GGUF quantizations of a LoRA fine-tune of meta-llama/Llama-3.2-3B-Instruct, trained with GRPO (reinforcement learning) on AI-MO/NuminaMath-CoT.

Quantized from ermiaazarkhalili/Llama-3.2-3B-Instruct-GRPO-NuminaMath-10K. See that repository for the full-precision weights.

| | |

| --- | --- |

| Base model | meta-llama/Llama-3.2-3B-Instruct |

| Training data | AI-MO/NuminaMath-CoT |

| Method | LoRA GRPO (reinforcement learning) via Unsloth + TRL |

| License | llama3.2 (inherited from the base model) |

Available quantizations

| File | Size |

| --- | --- |

| llama-3.2-3b-instruct-grpo-numinamath-10k.q4_k_m.gguf | 2.02 GB |

| llama-3.2-3b-instruct-grpo-numinamath-10k.q5_k_m.gguf | 2.32 GB |

| llama-3.2-3b-instruct-grpo-numinamath-10k.q8_0.gguf | 3.42 GB |

Usage

llama.cpp

huggingface-cli download ermiaazarkhalili/Llama-3.2-3B-Instruct-GRPO-NuminaMath-10K-GGUF llama-3.2-3b-instruct-grpo-numinamath-10k.q4_k_m.gguf --local-dir .
llama-cli -m llama-3.2-3b-instruct-grpo-numinamath-10k.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256

Ollama

echo 'FROM ./llama-3.2-3b-instruct-grpo-numinamath-10k.q4_k_m.gguf' > Modelfile
ollama create llama-3.2-3b-instruct-grpo-numinamath-10k-gguf -f Modelfile
ollama run llama-3.2-3b-instruct-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.