Downloads · 30 days
25
7% of all-time downloads
jacobbabula/bailiwick-misty-qwen3-0.6b-v20
bailiwick-misty-qwen3-0.6b-v20 is a text generation model from jacobbabula. Use it when you need the model to write or continue text. It is set up for transformers.js. The card lists the license as apache-2.0.
Misty v20 is Bailiwick's compact bilingual language-tutoring model for local browser inference. It is a fine-tuned Qwen/Qwen3-0.6B model exported to ONNX and packaged as a 4-bit WebGPU-compatible Transformers.js artif…
Downloads · 30 days
25
7% of all-time downloads
All-time downloads
338
Public
Repo size
1 GB
Likes
1
Public
Click a slice to open those files.
.onnx_data995 MB · 98%
From the Hugging Face model README
Misty v20 is Bailiwick's compact bilingual language-tutoring model for local browser inference. It is a fine-tuned Qwen/Qwen3-0.6B model exported to ONNX and packaged as a 4-bit WebGPU-compatible Transformers.js artifact.
@huggingface/transformers with WebGPU.The Bailiwick application supplies reviewed curriculum context, enforces the learner's requested response language, keeps active graded answers out of model context, and validates visible output. This model is not intended to grade learners or operate as an answer key by itself.
Qwen/Qwen3-0.6B at pinned revision c1899de289a04d12100db370d81485cdf75e47ca.These results describe the tested Bailiwick system candidate, not a claim of perfect standalone-model accuracy. Language tutoring should remain grounded in reviewed curriculum, and consequential grading decisions must not be delegated to the model.
Transformers.js loads the repository root as the model and uses:
onnx/model_q4.onnxonnx/model_q4.onnx_dataThe exact file sizes and SHA-256 values are recorded in browser-export-manifest.json.
Apache License 2.0. The base model is also distributed under Apache-2.0.