Update README.md
Browse files
README.md
CHANGED
|
@@ -45,6 +45,12 @@ Hammer models offer flexibility in deployment and usage, fully supporting both *
|
|
| 45 |
|
| 46 |
### Using vLLM
|
| 47 |
#### Option 1: Using Hammer client
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
vLLM offers efficient serving with lower latency. To serve the model with vLLM:
|
| 49 |
```
|
| 50 |
vllm serve MadeAgents/Hammer2.1-1.5b --host 0.0.0.0 --port 8000 --tensor-parallel-size 1
|
|
|
|
| 45 |
|
| 46 |
### Using vLLM
|
| 47 |
#### Option 1: Using Hammer client
|
| 48 |
+
Before using vLLM, first clone the Hammer code repository and change directory to the 'Hammer':
|
| 49 |
+
```
|
| 50 |
+
git clone https://github.com/MadeAgents/Hammer.git
|
| 51 |
+
cd Hammer
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
vLLM offers efficient serving with lower latency. To serve the model with vLLM:
|
| 55 |
```
|
| 56 |
vllm serve MadeAgents/Hammer2.1-1.5b --host 0.0.0.0 --port 8000 --tensor-parallel-size 1
|