Upload folder using huggingface_hub

.gitattributes

@@ -34,4 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
-Qwen3-1.7B-rk3588-w8a8-opt-0-hybrid-ratio-1.0.rkllm filter=lfs diff=lfs merge=lfs -text
+Qwen3-1.7B-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm filter=lfs diff=lfs merge=lfs -text

Qwen3-1.7B-rk3588-w8a8_g128-opt-0-hybrid-ratio-0.0.rkllm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d97ae5a7fbea20c0c1d73bbfaccfcb725925b863425ab8a18204a18bf827c5
+size 2582055492

README.md

@@ -8,7 +8,7 @@ pipeline_tag: text-generation
 ---
 # Qwen3-1.7B-RK3588-1.2.1
 
-This version of Qwen3-1.7B has been converted to run on the RK3588 NPU using w8a8 quantization.
+This version of Qwen3-1.7B has been converted to run on the RK3588 NPU using w8a8_g128 quantization.
 
 This model has been optimized with the following LoRA: