Upload optimized language model w/ WebGPU-compatible GQA (#29) e6c9dea verified Xenova HF Staff commited on 19 days ago
Upload fp16/q4f16 decoder ONNX weights w/ float32 inputs_embeds (#15) 7fb3550 verified Xenova HF Staff commited on Dec 2, 2024
Upload ONNX weights + chat template fixes (#13) 68141df verified andito HF Staff Xenova HF Staff commited on Dec 1, 2024