Text Generation
Safetensors
English
qwen3_5
grug
reasoning
token-efficient
agentic
tool-use
conversational
Instructions to use ProCreations/grug-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
Download preprocessor_config.json from ProCreations/grug-27b: direct link, hf CLI and curl.
- Browser
- Download file 390 Bytes
-
https://huggingface.co/ProCreations/grug-27b/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://ProCreations/grug-27b/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/ProCreations/grug-27b/resolve/main/preprocessor_config.json
390 Bytes
| { | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "image_processor_type": "Qwen2VLImageProcessorFast" | |
| } |