We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 53b055b commit 722e688Copy full SHA for 722e688
README.md
@@ -255,14 +255,15 @@ python fp8_cast_bf16.py --input-fp8-hf-path /path/to/fp8_weights --output-bf16-h
255
256
#### System Requirements
257
258
-OS: Linux (Mac, Windows are currently not supported)
259
-
260
-- Python 3.10
261
-- PyTorch 2.4.1
262
-- Transformers 4.46.3
263
-- Safetensors 0.4.5
264
-- Triton 3.0.0
+:warning: **Mac, Windows are currently not supported**: OS: Linux + Python 3.10
265
+Dependencies:
+```
+torch==2.4.1
+triton==3.0.0
+transformers==4.46.3
+safetensors==0.4.5
266
267
#### Model Weights & Demo Code Preparation
268
269
First, clone our DeepSeek-V3 GitHub repository:
0 commit comments