qwen1.5-moe-a2.7b-chat (Keras 3, bf16)
Pure-Keras 3 conversion of Qwen/Qwen1.5-MoE-A2.7B-Chat 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("qwen1.5-moe-a2.7b-chat")
tokenizer = Qwen2MoeTokenizer.from_weights("qwen1.5-moe-a2.7b-chat")
- Downloads last month
- 13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for kerasformers/qwen1.5-moe-a2.7b-chat
Base model
Qwen/Qwen1.5-MoE-A2.7B-Chat