mlx-community
/

Qwen3-Embedding-8B-4bit-DWQ

depasquale commited on Jun 23

Commit

885642d

verified ·

1 Parent(s): c65efdf

Update config.json (#3)

- Update config.json (64bf224f2fd7976e6d0158a39734b96e9fecad5c)

Co-authored-by: Anthony <depasquale@users.noreply.huggingface.co>

Files changed (1) hide show

config.json CHANGED Viewed

@@ -29,7 +29,7 @@
     "rope_scaling": null,
     "rope_theta": 1000000,
     "sliding_window": null,
-    "tie_word_embeddings": false,
     "torch_dtype": "bfloat16",
     "transformers_version": "4.51.2",
     "use_cache": true,

     "rope_scaling": null,
     "rope_theta": 1000000,
     "sliding_window": null,
+    "tie_word_embeddings": true,
     "torch_dtype": "bfloat16",
     "transformers_version": "4.51.2",
     "use_cache": true,