README.md

metadata

license: apache-2.0
language:
  - en
library_name: transformers.js
tags:
  - code
  - python
  - maincoder
  - code-generation
  - reinforcement-learning
  - mcpo
  - onnx
pipeline_tag: text-generation
base_model: Maincode/Maincoder-1B

Maincoder 1B — ONNX (Quantized, WebGPU)

This is a quantized ONNX version of Maincode/Maincoder-1B, optimized for in-browser inference with Transformers.js and WebGPU.

Quantization

• Format: ONNX with int4 (MatMulNBits) quantization
• Original model size: ~5 GB (fp32)
• Quantized model size: ~1.5 GB (q4)
• Quantization method: MatMulNBitsQuantizer from onnxruntime with block_size=32, symmetric quantization

All tensor data is embedded in a single .onnx file (no external data files) for browser compatibility.

Usage with Transformers.js

import { AutoModelForCausalLM, AutoTokenizer } from "@huggingface/transformers";

const model = await AutoModelForCausalLM.from_pretrained(
  "shreyask/Maincoder-1B-ONNX-web",
  { dtype: "q4", device: "webgpu" }
);

const tokenizer = await AutoTokenizer.from_pretrained(
  "shreyask/Maincoder-1B-ONNX-web"
);

const messages = [
  { role: "system", content: "You are Maincoder, an expert code generation assistant." },
  { role: "user", content: "Write a binary search function in Python" },
];

const input = tokenizer.apply_chat_template(messages, {
  add_generation_prompt: true,
  return_dict: true,
});

const output = await model.generate({
  ...input,
  max_new_tokens: 1024,
  eos_token_id: [151643, 151645],
});

Base Model

This is a quantized conversion of Maincode/Maincoder-1B. See the base model card for training details, benchmarks, and intended use.