inference-optimization
/

DeepSeek-R1-NVFP4-FP8-BLOCK

8-bit precision

compressed-tensors

Model card Files Files and versions

bdellabe commited on 4 days ago

Commit

2de23b5

·

verified ·

1 Parent(s): 9dc4ae1

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ sampling_params = SamplingParams(
     temperature=0.80, top_p=0.95, max_tokens=40, min_tokens=10
 )
 llm = LLM(
-    "bdellabe/DeepSeek-R1-NVFP4-FP8-BLOCK",
     tensor_parallel_size=4,
     max_model_len=4096,
     enforce_eager=True,

     temperature=0.80, top_p=0.95, max_tokens=40, min_tokens=10
 )
 llm = LLM(
+    "inference-optimization/DeepSeek-R1-NVFP4-FP8-BLOCK",
     tensor_parallel_size=4,
     max_model_len=4096,
     enforce_eager=True,