Instructions to use Azimml/Qwen3-1.7B-trellis-3bit-webgpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Azimml/Qwen3-1.7B-trellis-3bit-webgpu with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Azimml/Qwen3-1.7B-trellis-3bit-webgpu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 810 Bytes
eef05d7 | 1 | {"model.embed_tokens.weight.bits": {"offset": 0, "shape": [1215488, 24], "dtype": "u32", "shard": "emb.bin"}, "model.embed_tokens.weight.su": {"offset": 116686848, "shape": [2048], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.sv": {"offset": 116690944, "shape": [151936], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.isc": {"offset": 116994816, "shape": [2048], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.osc": {"offset": 116998912, "shape": [151936], "dtype": "f16", "shard": "emb.bin"}, "model.embed_tokens.weight.scale": {"offset": 117302784, "shape": [1], "dtype": "f32", "shard": "emb.bin"}, "model.embed_tokens.weight": {"quant": true, "n_out": 151936, "k_in": 2048, "K": 3, "block": 128, "tiles_out": 9496, "tiles_in": 128, "shard": "emb.bin"}} |