Base Model: google/gemma-2b-it
LoRA Rank: 16
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Task: Python Code Generation

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model and tokenizer
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")

# Load LoRA adapter
model = PeftModel.from_pretrained(model, "rohitnagareddy/gemma-2b-python-expert-lora")

# Generate Python code
prompt = "Write a Python function to implement binary search:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Capabilities

Clean, documented Python code
Type hints and error handling
PEP 8 compliance
Algorithm implementation
Web development
Data processing
Testing and debugging

Citation

bibtex

@misc{sakana2024texttolora,
    title={Text-to-LoRA},
    author={Sakana AI},
    year={2024},
    url={https://github.com/SakanaAI/text-to-lora}
}