Downloads · 30 days
0
TinyLlama-1.1B-Chat-v1.0-webgpu-v2
lwanming/TinyLlama-1.1B-Chat-v1.0-webgpu-v2
TinyLlama-1.1B-Chat-v1.0-webgpu-v2 is a machine learning model from lwanming. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Build with onnxruntime-genai at head of commit: da58e20df8b33e4ea8638798232720c834d798c1, and with this PR applied.
Access
Public
Updated Nov 21, 2025
Repo size
620 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data619 MB · 99%
At a glance
- Access
- Public
- Created
- Nov 21, 2025
- Updated
- Nov 21, 2025
- SHA
- eceb69e8
Model card
From the Hugging Face model README
Build with onnxruntime-genai at head of commit: da58e20df8b33e4ea8638798232720c834d798c1, and with this PR applied.
python builder.py -m TinyLlama/TinyLlama-1.1B-Chat-v1.0 -o TinyLlama-1.1B-Chat-v1.0-webgpu-v2 -c honry-cache-dir -p int4 -e webgpu --extra_options int4_block_size=32 int4_accuracy_level=4 int4_op_types_to_quantize=MatMul/Gather enable_webgpu_graph=true
- Created
- Nov 21, 2025
- Updated
- Nov 21, 2025