Instructions to use Prince-1/SmolVLM-Instruct-GGUF-RKllm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- RKLLM
How to use Prince-1/SmolVLM-Instruct-GGUF-RKllm with RKLLM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
SmolVLM rkllm conversion
Thank you very much for providing the RKLLM engine.
I attempted to convert SmolVLM to RKLLM, but the text decoder only produced meaningless garbage output.
Could you please share your thoughts on what I might have done wrong?
Thank you very much for your time and insight.
Can you please show me your script and output
Thanks for your comment.
—
It seems that the safetensors file of the SmolVLM model I downloaded via the Hugging Face Python API was outdated.
After manually downloading the model.safetensors file directly from the following URL, everything worked perfectly:
• https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/tree/main
I hope this helps anyone experiencing the same issue.
I build the rkllm using version 1.2.1 .let. Me rebuild this with latest version , and check if it's still showing the issue.