Files changed (1) hide show
  1. README.md +3 -35
README.md CHANGED
@@ -32,6 +32,9 @@ library_name: transformers
32
 
33
  # ERNIE-4.5-300B-A47B-Base
34
 
 
 
 
35
  ## ERNIE 4.5 Highlights
36
 
37
  The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
@@ -61,41 +64,6 @@ ERNIE-4.5-300B-A47B-Base is a text MoE Base model, with 300B total parameters an
61
 
62
  ## Quickstart
63
 
64
- ### Model Finetuning with ERNIEKit
65
-
66
- [ERNIEKit](https://github.com/PaddlePaddle/ERNIE) is a training toolkit based on PaddlePaddle, specifically designed for the ERNIE series of open-source large models. It provides comprehensive support for scenarios such as instruction fine-tuning (SFT, LoRA) and alignment training (DPO), ensuring optimal performance.
67
-
68
- Usage Examples:
69
-
70
- ```bash
71
- # Download model
72
- huggingface-cli download baidu/ERNIE-4.5-300B-A47B-Base-Paddle --local-dir baidu/ERNIE-4.5-300B-A47B-Base-Paddle
73
- # SFT
74
- erniekit train examples/configs/ERNIE-4.5-300B-A47B/sft/run_sft_wint8mix_lora_8k.yaml model_name_or_path=baidu/ERNIE-4.5-300B-A47B-Base-Paddle
75
- # DPO
76
- erniekit train examples/configs/ERNIE-4.5-300B-A47B/dpo/run_dpo_wint8mix_lora_8k.yaml model_name_or_path=baidu/ERNIE-4.5-300B-A47B-Base-Paddle
77
- ```
78
-
79
- For more detailed examples, including SFT with LoRA, multi-GPU configurations, and advanced scripts, please refer to the examples folder within the [ERNIEKit](https://github.com/PaddlePaddle/ERNIE) repository.
80
-
81
- ### Using FastDeploy
82
-
83
- Service deployment can be quickly completed using FastDeploy in the following command. For more detailed usage instructions, please refer to the [FastDeploy Repository](https://github.com/PaddlePaddle/FastDeploy).
84
-
85
- **Note**: To deploy on a configuration with 4 GPUs each having at least 80G of memory, specify ```--quantization wint4```. If you specify ```--quantization wint8```, then resources for 8 GPUs are required.
86
-
87
- ```bash
88
- python -m fastdeploy.entrypoints.openai.api_server \
89
- --model baidu/ERNIE-4.5-300B-A47B-Base-Paddle \
90
- --port 8180 \
91
- --metrics-port 8181 \
92
- --engine-worker-queue-port 8182 \
93
- --quantization wint4 \
94
- --tensor-parallel-size 8 \
95
- --max-model-len 32768 \
96
- --max-num-seqs 32
97
- ```
98
-
99
  ### Using `transformers` library
100
 
101
  **Note**: Before using the model, please ensure you have the `transformers` library installed (version 4.50.0 or higher)
 
32
 
33
  # ERNIE-4.5-300B-A47B-Base
34
 
35
+ > [!NOTE]
36
+ > Note: "**-Paddle**" models use [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) weights, while "**-PT**" models use Transformer-style PyTorch weights.
37
+
38
  ## ERNIE 4.5 Highlights
39
 
40
  The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
 
64
 
65
  ## Quickstart
66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  ### Using `transformers` library
68
 
69
  **Note**: Before using the model, please ensure you have the `transformers` library installed (version 4.50.0 or higher)