Qwen
/

Qwen3-Embedding-8B

Feature Extraction

sentence-transformers

text-generation

sentence-similarity

text-embeddings-inference

Model card Files Files and versions

alvarobartt HF Staff commited on Jun 8, 2025

Commit

c544677

·

verified ·

1 Parent(s): 6ee130c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -72,7 +72,7 @@ model = SentenceTransformer("Qwen/Qwen3-Embedding-8B")
 # together with setting `padding_side` to "left":
 # model = SentenceTransformer(
 #     "Qwen/Qwen3-Embedding-8B",
-#     model_kwargs={"attn_implementation": "flash_attention_2", "torch_type": "float16", "device_map": "auto"},
 #     tokenizer_kwargs={"padding_side": "left"},
 # )

 # together with setting `padding_side` to "left":
 # model = SentenceTransformer(
 #     "Qwen/Qwen3-Embedding-8B",
+#     model_kwargs={"attn_implementation": "flash_attention_2", "torch_dtype": "float16", "device_map": "auto"},
 #     tokenizer_kwargs={"padding_side": "left"},
 # )