RedHatAI
/

Llama-3.1-8B-Instruct-speculator.eagle3

Text Generation

Model card Files Files and versions

alexmarques commited on 11 days ago

Commit

49a1870

·

verified ·

1 Parent(s): ffd801c

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -158,7 +158,8 @@ vllm serve meta-llama/Llama-3.1-8B-Instruct \
 GUIDELLM__PREFERRED_ROUTE="chat_completions" \
 guidellm benchmark \
   --target "http://localhost:8000/v1" \
-  --data "RedHatAI/SpeculativeDecoding" \
   --rate-type sweep \
   --max-seconds 180 \
   --output-path "Llama-3.1-8B-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 180 \
   --output-path "Llama-3.1-8B-Instruct-HumanEval.json" \