Downloads · 30 days
14
15% of all-time downloads
prompt-enhancer-clarity-lora
felipemunoz/prompt-enhancer-clarity-lora
prompt-enhancer-clarity-lora is a machine learning model from felipemunoz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
QLoRA adapter (rank=32) for Qwen2.5-1.5B-Instruct, fine-tuned to improve prompt clarity. Converted to GGUF LoRA format for use with llama-cpp-python.
All-time downloads
93
Public
Repo size
233 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors148 MB · 63%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026
- SHA
- 03fbe9e8
Model card
From the Hugging Face model README
Prompt Enhancer Clarity LoRA Adapter
QLoRA adapter (rank=32) for Qwen2.5-1.5B-Instruct, fine-tuned to improve prompt clarity. Converted to GGUF LoRA format for use with llama-cpp-python.
Training Metrics
| Parameter | Value |
|---|---|
| data_path | /home/felipe/hook_prompt_enhancer/training/data/clarity_train.jsonl |
| data_splits | {'train': 990, 'val': 110} |
| hyperparameters | {'learning_rate': 0.0005, 'batch_size': 1, 'epochs': 1, 'lora_r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'gradient_accumulation_steps': 1, 'weight_decay': 0.01, 'warmup_ratio': None, 'time_budget': 300} |
| model_name | Qwen/Qwen2.5-1.5B-Instruct |
| seed | 42 |
| stage | clarity |
| timestamp | 2026-03-28T09:09:31.326409+00:00 |
| val_loss | 0.3387 |
Usage
from llama_cpp import Llama
llm = Llama(
model_path="qwen2.5-1.5b-instruct-q4_k_m.gguf",
lora_path="clarity-lora.gguf",
)
output = llm("Improve this prompt: ...")
License
Apache-2.0
- License
- apache-2.0
- Languages
- en
- Created
- Mar 28, 2026
- Updated
- Mar 28, 2026