ermiaazarkhalili/Ornith-1.5-9B-SFT-Fable5-Glint-GGUF

Ornith-1.5-9B-SFT-Fable5-Glint-GGUF

GGUF quantizations of a LoRA fine-tune of `ornith-ai/Ornith-1.5-9B`, supervised fine-tuned on ermiaazarkhalili/Fable-5-Glint-Clean (private).

Quantized from `ermiaazarkhalili/Ornith-1.5-9B-SFT-Fable5-Glint`. See that repository for the full-precision weights.

Available quantizations

Usage

llama.cpp

huggingface-cli download ermiaazarkhalili/Ornith-1.5-9B-SFT-Fable5-Glint-GGUF ornith-1.5-9b-sft-fable5-glint.q4_k_m.gguf --local-dir .
llama-cli -m ornith-1.5-9b-sft-fable5-glint.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256

Ollama

echo 'FROM ./ornith-1.5-9b-sft-fable5-glint.q4_k_m.gguf' > Modelfile
ollama create ornith-1.5-9b-sft-fable5-glint-gguf -f Modelfile
ollama run ornith-1.5-9b-sft-fable5-glint-gguf

Training configuration

Observed training loss

Measured from our SLURM logs for this configuration. These are training-loss observations only — no downstream benchmark evaluation has been run on this model, so they should not be read as a quality claim.

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

Trained by notebooks/fable_distillation_ornith-1.5-9b_fable-glint_unsloth.ipynb, executed non-interactively with papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).

Card generated from the training run's own configuration and logs by `scripts/generate_hub_model_card.py`.