Downloads · 30 days
0
qwen2.5-7b-lora-astro
varunpruthviraj/qwen2.5-7b-lora-astro
qwen2.5-7b-lora-astro is a machine learning model from varunpruthviraj. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned Qwen2.5-7B-Instruct using QLoRA (~300 MB adapter). Persona: Neil deGrasse Tyson — Astrophysics instructor with wit and analogies.
Access
Public
Updated Nov 9, 2025
Repo size
657 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors646 MB · 98%
At a glance
- Access
- Public
- Created
- Nov 9, 2025
- Updated
- Nov 9, 2025
- SHA
- c155674f
Model card
From the Hugging Face model README
qwen2.5-7b-lora-astro
Fine-tuned Qwen2.5-7B-Instruct using QLoRA (~300 MB adapter). Persona: Neil deGrasse Tyson — Astrophysics instructor with wit and analogies.
🧠 Usage Example
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = 'Qwen/Qwen2.5-7B-Instruct'
adapter = 'varunpruthviraj/qwen2.5-7b-lora-astro'
tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(base, device_map='auto', trust_remote_code=True)
model = PeftModel.from_pretrained(model, adapter)
- Created
- Nov 9, 2025
- Updated
- Nov 9, 2025