tatsuya4

In real-world use cases, it seems more appropriate to use advanced models to generate suitable rule trees or regular expressions for processing HTML → Markdown, rather than directly using a smaller model to handle each HTML instance. The reasons for this approach include:

1. The quality of HTML → Markdown conversion results is easier to evaluate.

2. The HTML → Markdown process is essentially a more sophisticated form of copy-and-paste, where AI generates specific symbols (such as ##, *) rather than content.

3. Rule-based systems are significantly more cost-effective and faster than running an LLM, making them applicable to a wider range of scenarios.

These are just my assumptions and judgments. If you have practical experience, I'd welcome your insights.

It appears that no inference provider currently supports the 72B version.

ModelBox have a playground for Qwen Math

7B: https://model.box/try/playground/qwen/qwen2-math-7b-instruct 1.5b: https://model.box/try/playground/qwen/qwen2-math-1.5b-instru...

Did you use the LLM aggregator like https://model.box ?

Just did a quick test in the https://model.box playground, and it looks like the completion length is noticeably shorter than other models (e.g., gpt-4o). However, the response speed meets expectations..