How to input images to example Qwen3.5?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
Excuse me, I failed to run llama.runner.native in qwen3_5 example instruction. (as #18832) But I managed to run qwen3.5-0.8B with instruction of llama.
If I'm not mistaken, the entire Qwen 3.5 series are VLMs (which support images) and not just LLMs. I wonder if I can input images to this example now? If so, what should I do for this?
Thank you！
cc @larryliu0820 @mergennachin @cccclai @helunwencser @jackzhxng
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the examples/models/qwen3_5 README and compare its instructions with examples/models/llama, especially the llama.runner.native entry point. Determine whether the current Qwen3.5 example exposes image input and what model or preprocessing requirements apply. Done should be a confirmed procedure documented in the example, or a clearly scoped implementation plan if image input is unsupported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100