config.json add "tie_word_embeddings": true (#7)

- config.json add "tie_word_embeddings": true (3a2dba6387cabdaa7b895ff944ceef408232b5f2)
- minor update to readme (2112044c45d8a784e5eec33d02b95b5d22222aa8)


Co-authored-by: ckl <[email protected]>

README.md

@@ -68,8 +68,7 @@ ERNIE-4.5-0.3B is a text dense Post-trained model. The following are the model c
 
 ### Using `transformers` library
 
-**Note**: Before using the model, please ensure you have the `transformers` library installed
-(upcoming version 4.54.0 or [the latest version](https://github.com/huggingface/transformers?tab=readme-ov-file#installation))
+**Note**: You'll need the `transformers` library (version 4.54.0 or newer) installed to use this model.
 
 The following contains a code snippet illustrating how to use the model generate content based on given inputs.
 
@@ -116,7 +115,7 @@ print("generate_text:", generate_text)
 [vllm](https://github.com/vllm-project/vllm/tree/main) github library. Python-only [build](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#set-up-using-python-only-build-without-compilation).
 
 ```bash
-vllm serve baidu/ERNIE-4.5-0.3B-PT --trust-remote-code
+vllm serve baidu/ERNIE-4.5-0.3B-PT
 ```
 
 ## License

config.json

@@ -18,6 +18,7 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.0.dev0",
   "use_bias": false,