Downloads · 30 days
77
13% of all-time downloads
Qwen3.5-9B-SFT-Fable5-GGUF
ermiaazarkhalili/Qwen3.5-9B-SFT-Fable5-GGUF
Qwen3.5-9B-SFT-Fable5-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 apache-2.0.
GGUF quantizations of a LoRA fine-tune of unsloth/Qwen3.5-9B, supervised fine-tuned on ermiaazarkhalili/Fable-5-Complete-2M-Clean (private).
All-time downloads
572
Public
Repo size
21.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf21.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Aug 4, 2026
- SHA
- 43b14765
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5-9B-SFT-Fable5-GGUF
GGUF quantizations of a LoRA fine-tune of unsloth/Qwen3.5-9B, supervised fine-tuned on ermiaazarkhalili/Fable-5-Complete-2M-Clean (private).
Quantized from ermiaazarkhalili/Qwen3.5-9B-SFT-Fable5. See that repository for the full-precision weights.
| Base model | unsloth/Qwen3.5-9B |
| Training data | ermiaazarkhalili/Fable-5-Complete-2M-Clean (private) |
| Method | LoRA supervised fine-tuning via Unsloth + TRL |
| License | apache-2.0 (inherited from the base model) |
Available quantizations
| File | Size |
|---|---|
qwen3.5-9b-sft-fable5.q4_k_m.gguf | 5.63 GB |
qwen3.5-9b-sft-fable5.q5_k_m.gguf | 6.47 GB |
qwen3.5-9b-sft-fable5.q8_0.gguf | 9.53 GB |
Usage
llama.cpp
huggingface-cli download ermiaazarkhalili/Qwen3.5-9B-SFT-Fable5-GGUF qwen3.5-9b-sft-fable5.q4_k_m.gguf --local-dir .
llama-cli -m qwen3.5-9b-sft-fable5.q4_k_m.gguf -p "Explain gradient checkpointing in two sentences." -n 256
Ollama
echo 'FROM ./qwen3.5-9b-sft-fable5.q4_k_m.gguf' > Modelfile
ollama create qwen3.5-9b-sft-fable5-gguf -f Modelfile
ollama run qwen3.5-9b-sft-fable5-gguf
Training configuration
| Setting | Value |
|---|---|
| LoRA rank (r) | 16 |
| LoRA alpha | 16 |
| Learning rate | 0.0002 |
| Epochs | 1 |
| Effective batch size | 8 (1 x 8 grad accum) |
| Max sequence length | 4096 |
| Base precision | 4-bit (QLoRA) |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, out_proj |
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.
| SLURM job | Steps | First loss | Final loss |
|---|---|---|---|
| unlabelled | 47,127 | 0.9168 | 0.8932 |
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_qwen35-9b_fable_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.
- Task
- Text Generation
- Library
- gguf
- License
- apache-2.0
- Created
- Jul 10, 2026
- Updated
- Aug 4, 2026