Update README.md
Browse files
README.md
CHANGED
|
@@ -64,6 +64,28 @@ Watch the JiRack Coder 32B in action:
|
|
| 64 |
|
| 65 |
---
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
## Access the UI
|
| 68 |
Once the container is running, open your browser and navigate to:
|
| 69 |
|
|
|
|
| 64 |
|
| 65 |
---
|
| 66 |
|
| 67 |
+
services:
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
image: cmsmanhattan/jirack_coder_32b_int4_gpu_qwenbase:latest
|
| 71 |
+
container_name: jirack_onnx_service
|
| 72 |
+
ports:
|
| 73 |
+
- "7869:7869"
|
| 74 |
+
volumes:
|
| 75 |
+
- .:/app
|
| 76 |
+
- ./web:/app/web
|
| 77 |
+
environment:
|
| 78 |
+
- MAX_TOKENS=1024
|
| 79 |
+
- TEMPERATURE=0.7
|
| 80 |
+
- TOP_P=0.9
|
| 81 |
+
- DEFAULT_STREAM=False
|
| 82 |
+
- INTRA_THREADS=4
|
| 83 |
+
- USE_ENV_ALLOCATOR=1
|
| 84 |
+
deploy:
|
| 85 |
+
resources:
|
| 86 |
+
limits:
|
| 87 |
+
memory: 16g
|
| 88 |
+
|
| 89 |
## Access the UI
|
| 90 |
Once the container is running, open your browser and navigate to:
|
| 91 |
|