haydso/Qwen3-0.6B-Reverse-Text-SFT-ONNX

Qwen3-0.6B-Reverse-Text-SFT (ONNX)

This is an ONNX version of PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT. It was converted using the ONNX Runtime GenAI builder.

Conversion Details

• Precision: int4

• Execution Provider: webgpu

• Base Model: PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT

Usage with ONNX Runtime GenAI

import onnxruntime_genai as og

# Load the model

model = og.Model("haydso/Qwen3-0.6B-Reverse-Text-SFT-ONNX")

tokenizer = og.Tokenizer(model)

# Generate text

prompt = "Your prompt here"

tokens = tokenizer.encode(prompt)

params = og.GeneratorParams(model)

params.set_search_options(max_length=200)

params.input_ids = tokens

generator = og.Generator(model, params)

while not generator.is_done():

    generator.compute_logits()

    generator.generate_next_token()

output_tokens = generator.get_sequence(0)

text = tokenizer.decode(output_tokens)

print(text)

Original Model Card

Qwen3-0.6B-Reverse-Text-SFT

A SFT fine-tune of PrimeIntellect/Qwen3-0.6B. Details here.