qwen2-57b-a14b (Keras 3, bf16)
Pure-Keras 3 conversion of Qwen/Qwen2-57B-A14B for kerasformers. Apache 2.0.
This repo holds the converted model weights and tokenizer.json.
from kerasformers.models.qwen2_moe import Qwen2MoeGenerate, Qwen2MoeTokenizer
model = Qwen2MoeGenerate.from_weights("qwen2-57b-a14b")
tokenizer = Qwen2MoeTokenizer.from_weights("qwen2-57b-a14b")
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for KerasFormers/qwen2-57b-a14b
Base model
Qwen/Qwen2-57B-A14B