Update README.md
Browse files
README.md
CHANGED
|
@@ -103,6 +103,17 @@ We have also specifically optimized AntAngelMed for inference acceleration by em
|
|
| 103 |
|
| 104 |
# Quickstart
|
| 105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
## 🤗 Hugging Face Transformers
|
| 107 |
|
| 108 |
Here is a code snippet to show you how to use the chat model with transformers:
|
|
|
|
| 103 |
|
| 104 |
# Quickstart
|
| 105 |
|
| 106 |
+
## Deployment Configuration
|
| 107 |
+
|
| 108 |
+
| Model | Precision | Total Parameters | Active Parameters | Hardware | Recommended Cards | Download URL |
|
| 109 |
+
|---|---|---|---|---|---:|---|
|
| 110 |
+
| AntAngelMed-100B | BF16 | 100B | 6B | Ascend 昇腾910B (64GB) | 8 | [ModelScope](https://modelscope.cn/models/MedAIBase/AntAngelMed) |
|
| 111 |
+
| | | | | Kunlun Core (昆仑芯) P800 (96GB) | 4 | |
|
| 112 |
+
| | | | | PPU 810 (96GB) | 4 | |
|
| 113 |
+
| AntAngelMed-INT4 | INT4 | 100B | 6B | Ascend 昇腾910B (64GB) | 2 | [ModelScope](https://modelscope.cn/models/MedAIBase/AntAngelMed-INT4) |
|
| 114 |
+
| | | | | Kunlun Core (昆仑芯) P800 (96GB) | 1 | |
|
| 115 |
+
| | | | | PPU 810 (96GB) | 1 | |
|
| 116 |
+
|
| 117 |
## 🤗 Hugging Face Transformers
|
| 118 |
|
| 119 |
Here is a code snippet to show you how to use the chat model with transformers:
|