YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Model Card for ShreyashSarkarDev/qwen3-0.6b-finetuned-alpaca
This is a fine-tuned version of the Qwen/Qwen1.5-0.5B model on the yahma/alpaca-cleaned dataset.
Model Details
- Base Model:
Qwen/Qwen1.5-0.5B - Fine-tuning Method:
QLoRA - Fine-tuning Quantization:
4-bit - Dataset:
yahma/alpaca-cleaned
Training Parameters
- Learning Rate:
2e-4 - Number of Training Epochs:
3 - Per Device Train Batch Size:
4 - Gradient Accumulation Steps:
4 - Optimizer:
paged_adamw_8bit - Learning Rate Scheduler Type:
cosine
GGUF Conversion
This model has been converted to the GGUF format with the following quantization:
- GGUF Quantization Type:
Q8_0
Usage
You can load and use this model with the Hugging Face transformers library and potentially with llama.cpp or other GGUF-compatible inference engines.
- Downloads last month
- 1
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support