Parrot Coder 🦜

Parrot Coder is a highly efficient, 200M parameter language model optimized for rapid code autocompletion and code generation tasks. Developed by Inserloft Research.

This repository contains the merged base model + LoRA adapters in .safetensors format, ready for direct inference using transformers.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "InserloftResearch/Parrot-Coder"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = "def fibonacci(n):"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

For GGUF versions, visit our Ollama Registry.