Modelpublic

monyschuk/Qwen3.5-4B-Claude-Opus-abliterated-VLM-MLX

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

1likes105downloads

Model Card

Qwen3.5 4B Claude Opus Abliterated — MLX VLM

Abliterated Qwen3.5 4B vision-language model, converted for mlx-swift-lm compatibility.

About

This model is derived from mlx-community/Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated-6bit. The original model works with mlx-vlm but had issues with mlx-swift-lm:

—❌ Text-only chat template (no image support)
—❌ Nested processor_config.json format

What was fixed

Issue	Fix
chat_template.jinja	Replaced with VLM-aware template handling image/video content arrays
processor_config.json	Added flat-format preprocessor_config.json for Qwen3VLProcessor

Usage with mlx-swift-lm

swift

import MLXVLM
import MLXLMCommon
import Tokenizers

let modelDir = URL(fileURLWithPath: "/path/to/model")
let container = try await VLMModelFactory.shared.loadContainer(
    from: modelDir,
    using: LocalTokenizerLoader()
)
let session = ChatSession(container)
let response = try await session.respond(
    to: "Describe the image",
    image: .url(URL(fileURLWithPath: "/path/to/image.jpg"))
)

Download

To get the complete model, download the weight files from the original repo, then replace the config files with the fixed versions from this repo.

Fixed by monyschuk/mlx-qwen-fix