Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,22 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
```
|
| 6 |
curl http://127.0.0.1:9000/loadmodel -X POST -H "Content-Type: application/json" -d '{"model_filename":"models/PRWKV7-cxa076-qwen3b-stage2final-ctx2048.pth","model_viewname":"PRWKV7-cxa076 Qwen 2.5 3B Stage2 FP8","model_strategy":"fp8", "template":"qwen", "endtoken":"<|im_end|>","default_temperature":"1.0", "default_top_p":"0.3"}'
|
| 7 |
```
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
Scalability test from small to large
|
| 6 |
+
|
| 7 |
+
ToDo for Me:
|
| 8 |
+
Qwen 2.5 14B
|
| 9 |
+
Qwen 2.5 7B
|
| 10 |
+
Qwen 2.5 3B
|
| 11 |
+
|
| 12 |
+
Phi-4 14B
|
| 13 |
+
Phi-4-mini 3.8B
|
| 14 |
+
|
| 15 |
+
Gemma 3 12B
|
| 16 |
+
Gemma 3 4B
|
| 17 |
+
|
| 18 |
+
Architecture: RWKV cxa076 (RWKV x070 based)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
```
|
| 22 |
curl http://127.0.0.1:9000/loadmodel -X POST -H "Content-Type: application/json" -d '{"model_filename":"models/PRWKV7-cxa076-qwen3b-stage2final-ctx2048.pth","model_viewname":"PRWKV7-cxa076 Qwen 2.5 3B Stage2 FP8","model_strategy":"fp8", "template":"qwen", "endtoken":"<|im_end|>","default_temperature":"1.0", "default_top_p":"0.3"}'
|
| 23 |
```
|