granite-3.2-2b-instruct/README.md

granite-3.2-2b-instruct

GenAI WebGPU Model

Generated using onnxruntime_genai.models.builder

• onnxruntime-genai commit: 41c4ce18fec1240c2f848725e31fbe8854010188
• transformers version: 4.57.0
• Precision: int4
• Execution Provider: webgpu

python -m onnxruntime_genai.models.builder -p int4 -e webgpu -m ibm-granite/granite-3.2-2b-instruct -o E:\ai-models\granite-3.2-2b-instruct\onnx-webgpu\ --extra_options int4_algo_config=rtn_last int4_is_symmetric=true prune_lm_head=true enable_webgpu_graph=true

GGUF Model

Downloaded from: ibm-research/granite-3.2-2b-instruct-GGUF