AutoScientist Competition — Language Model
Fine-tuned from Qwen/Qwen2.5-0.5B-Instruct on the language adapted dataset produced by Adaption Labs AutoScientist Challenge.
Training
- Method: QLoRA (4-bit NF4, r=32, alpha=64)
- Epochs: 3
- Learning rate: 0.0002
- Dataset quality: Grade A (Adaption Labs evaluation)
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Rishidar/autoscientist-language-qlora")
tokenizer = AutoTokenizer.from_pretrained("Rishidar/autoscientist-language-qlora")
- Downloads last month
- 94
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support