Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- TheDrummer/Behemoth-R1-123B-v2
|
| 4 |
+
---
|
| 5 |
+
python3 -m mlc_llm compile --quantization q4f16_1 --output 123b_r1.so . --overrides "tensor_parallel_shards=2" --device cuda
|
| 6 |
+
python3 -m mlc_llm chat --device cuda 123b_r1/ --model-lib /workspace/123b_r1.so
|