A LoRA fine-tune of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled trained on OpenClaw tool-call data — optimized for agentic reasoning with structured tool invocation.

The base model is a Claude 4.6 Opus reasoning distillation of Qwen3.5-27B. This fine-tune adds structured tool-calling capability in the OpenClaw XML format, making it suitable for local agentic deployments.

What It Does

This adapter teaches the model the OpenClaw tool-calling format — a structured XML-style invocation pattern used by the OpenClaw AI agent platform:

xml

<function_calls>
<invoke name="TOOL_NAME">
<parameter name="PARAM_NAME">value</parameter>
</invoke>
</function_calls>

Supported tools in training data: exec, read, write, edit, web_search, web_fetch, browser, memory_search, memory_get, message, cron, nodes, image, pdf, sessions_spawn, session_status

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("hertz-hwang/Qwen3.5-27B-OpenClaw-mlx-6.5bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)