Support Qwen2_5_VLForConditionalGeneration #12595
Merged
+1
−1
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Make sure to read the contributing guidelines before submitting a PR
Based on this discussion:
#11483 (comment)
for the language part we can use the same architecture as Qwen2VLForConditionalGeneration.
Additionally HimariO has the update for the qwen2_vl_surgery.py to support --model_type "qwen2.5vl"
https://github.com/HimariO/llama.cpp.qwen2vl/tree/qwen25-vl
python examples/llava/qwen2_vl_surgery.py <path_to_model> --data_type fp32 --model_type "qwen2.5vl"
Tested working, examples:
DevQuasar/Qwen.Qwen2.5-VL-7B-Instruct-GGUF
build/bin/llama-qwen2vl-cli -m ~/Downloads/Qwen.Qwen2.5-VL-3B-Instruct.Q4_K_M.gguf --mmproj qwen.qwen2.5-vl-3b-instruct-vision.gguf -p "Describe this image." --image ~/Downloads/flower.jpg