Qwen3-Embedding-4B-rbln-tp2 / tokenizer.json

Commit History

RBLN-CA25 compiled Qwen/Qwen3-Embedding-4B (num_devices=2, max_seq_len=8192, batch_size=16, attn_impl=flash_attn, partition=4096)
e0322df
verified

iAcloudEthan commited on