Downloads · 30 days
24
6% of all-time downloads
LFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K-GGUF
ermiaazarkhalili/LFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K-GGUF
LFM2.5-1.2B-Instruct-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 other.
GGUF quantizations of a LoRA fine-tune of LiquidAI/LFM2.5-1.2B-Instruct, trained with GRPO (reinforcement learning) on AI-MO/NuminaMath-CoT.
All-time downloads
384
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- other
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Aug 4, 2026
- SHA
- b41c0faf
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
LFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K-GGUF
GGUF quantizations of a LoRA fine-tune of LiquidAI/LFM2.5-1.2B-Instruct, trained with GRPO (reinforcement learning) on AI-MO/NuminaMath-CoT.
Quantized from ermiaazarkhalili/LFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K. See that repository for the full-precision weights.
| Base model | LiquidAI/LFM2.5-1.2B-Instruct |
| Training data | AI-MO/NuminaMath-CoT |
| Method | LoRA GRPO (reinforcement learning) via Unsloth + TRL |
| License | other (inherited from the base model) |
Available quantizations
| File | Size |
|---|---|
lfm2.5-1.2b-instruct-grpo-numinamath-10k.q4_k_m.gguf | 731 MB |
lfm2.5-1.2b-instruct-grpo-numinamath-10k.q5_k_m.gguf | 843 MB |
lfm2.5-1.2b-instruct-grpo-numinamath-10k.q8_0.gguf | 1.25 GB |
Usage
llama.cpp
huggingface-cli download ermiaazarkhalili/LFM2.5-1.2B-Instruct-GRPO-NuminaMath-10K-GGUF lfm2.5-1.2b-instruct-grpo-numinamath-10k.q4_k_m.gguf --local-dir .
llama-cli -m lfm2.5-1.2b-instruct-grpo-numinamath-10k.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256
Ollama
echo 'FROM ./lfm2.5-1.2b-instruct-grpo-numinamath-10k.q4_k_m.gguf' > Modelfile
ollama create lfm2.5-1.2b-instruct-grpo-numinamath-10k-gguf -f Modelfile
ollama run lfm2.5-1.2b-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.
- Task
- Text Generation
- Library
- gguf
- License
- other
- Created
- Jul 4, 2026
- Updated
- Aug 4, 2026