RedHatAI
/

Llama-3.3-70B-Instruct-speculator.eagle3

Text Generation

Model card Files Files and versions

alexmarques commited on 14 days ago

Commit

9f3485b

·

verified ·

1 Parent(s): be5001b

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -157,7 +157,8 @@ vllm serve meta-llama/Llama-3.3-70B-Instruct \
 GUIDELLM__PREFERRED_ROUTE="chat_completions" \
 guidellm benchmark \
   --target "http://localhost:8000/v1" \
-  --data "RedHatAI/SpeculativeDecoding" \
   --rate-type sweep \
   --max-seconds 240 \
   --output-path "Llama-3.3-70B-Instruct-HumanEval.json" \

 GUIDELLM__PREFERRED_ROUTE="chat_completions" \
 guidellm benchmark \
   --target "http://localhost:8000/v1" \
+  --data "RedHatAI/speculator_benchmarks" \
+  --data-args '{"data_files": "HumanEval.jsonl"}' \
   --rate-type sweep \
   --max-seconds 240 \
   --output-path "Llama-3.3-70B-Instruct-HumanEval.json" \