Update config.json (#15)
Browse files- Update config.json (dd15cfb90079d7cd428538ef75e01a8230c7ab75)
- minor update to readme (262fa420ec92a220874a928b6e557a72db72b4df)
Co-authored-by: ckl <[email protected]>
- README.md +2 -3
- config.json +1 -0
README.md
CHANGED
|
@@ -72,8 +72,7 @@ ERNIE-4.5-21B-A3B is a text MoE Post-trained model, with 21B total parameters an
|
|
| 72 |
|
| 73 |
### Using `transformers` library
|
| 74 |
|
| 75 |
-
**Note**:
|
| 76 |
-
(upcoming version 4.54.0 or [the latest version](https://github.com/huggingface/transformers?tab=readme-ov-file#installation))
|
| 77 |
|
| 78 |
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
|
| 79 |
|
|
@@ -120,7 +119,7 @@ print("generate_text:", generate_text)
|
|
| 120 |
[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).
|
| 121 |
|
| 122 |
```bash
|
| 123 |
-
vllm serve baidu/ERNIE-4.5-21B-A3B-PT
|
| 124 |
```
|
| 125 |
|
| 126 |
## License
|
|
|
|
| 72 |
|
| 73 |
### Using `transformers` library
|
| 74 |
|
| 75 |
+
**Note**: You'll need the `transformers` library (version 4.54.0 or newer) installed to use this model.
|
|
|
|
| 76 |
|
| 77 |
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
|
| 78 |
|
|
|
|
| 119 |
[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).
|
| 120 |
|
| 121 |
```bash
|
| 122 |
+
vllm serve baidu/ERNIE-4.5-21B-A3B-PT
|
| 123 |
```
|
| 124 |
|
| 125 |
## License
|
config.json
CHANGED
|
@@ -28,6 +28,7 @@
|
|
| 28 |
"rope_scaling": null,
|
| 29 |
"rope_theta": 500000.0,
|
| 30 |
"router_aux_loss_coef": 0.001,
|
|
|
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
"transformers_version": "4.54.0.dev0",
|
| 33 |
"use_bias": false,
|
|
|
|
| 28 |
"rope_scaling": null,
|
| 29 |
"rope_theta": 500000.0,
|
| 30 |
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
"torch_dtype": "bfloat16",
|
| 33 |
"transformers_version": "4.54.0.dev0",
|
| 34 |
"use_bias": false,
|