llmware/phi-3.5-onnx-qnn

作者 llmware

↓ 21 ♥ 1

创建时间: 2025-01-29 16:36:27+00:00

更新时间: 2025-02-14 11:37:18+00:00

文件 (27)

.gitattributes

README.md

ar128_cl4096_1_of_4_qnn_ctx.onnx ONNX

ar128_cl4096_2_of_4_qnn_ctx.onnx ONNX

ar128_cl4096_3_of_4_qnn_ctx.onnx ONNX

ar128_cl4096_4_of_4_qnn_ctx.onnx ONNX

ar1_cl4096_1_of_4_qnn_ctx.onnx ONNX

ar1_cl4096_2_of_4_qnn_ctx.onnx ONNX

ar1_cl4096_3_of_4_qnn_ctx.onnx ONNX

ar1_cl4096_4_of_4_qnn_ctx.onnx ONNX

config.json

dequantizer.onnx ONNX

genai_config.json

genai_config_removed_sliding_window.json

position-processor.onnx ONNX

quantizer.onnx ONNX

special_tokens_map.json

tokenizer.json

tokenizer_config.json

weight_sharing_model_1_of_4.serialized.bin

weight_sharing_model_1_of_4.serialized.json

weight_sharing_model_2_of_4.serialized.bin

weight_sharing_model_2_of_4.serialized.json

weight_sharing_model_3_of_4.serialized.bin

weight_sharing_model_3_of_4.serialized.json

weight_sharing_model_4_of_4.serialized.bin

weight_sharing_model_4_of_4.serialized.json