[Docs] Restore the AIME25 label so GLM-5.3 FP8 and BF16 scores render again (#36950)
This commit is contained in:
@@ -68,6 +68,14 @@ sgl-eval run gsm8k \\
|
|||||||
aime26_pct:
|
aime26_pct:
|
||||||
`# To install sgl-eval: pip install git+https://github.com/sgl-project/sgl-eval
|
`# To install sgl-eval: pip install git+https://github.com/sgl-project/sgl-eval
|
||||||
sgl-eval run aime26 \\
|
sgl-eval run aime26 \\
|
||||||
|
--model {{MODEL_NAME}} --api-key <api-key> \\
|
||||||
|
--n-repeats 16 --max-tokens 64000 \\
|
||||||
|
--temperature 1.0 --top-p 0.95 --thinking \\
|
||||||
|
--out-dir /sgl-workspace/logs \\
|
||||||
|
--base-url http://{{CURL_HOST}}:{{CURL_PORT}}/v1`,
|
||||||
|
aime25_pct:
|
||||||
|
`# To install sgl-eval: pip install git+https://github.com/sgl-project/sgl-eval
|
||||||
|
sgl-eval run aime25 \\
|
||||||
--model {{MODEL_NAME}} --api-key <api-key> \\
|
--model {{MODEL_NAME}} --api-key <api-key> \\
|
||||||
--n-repeats 16 --max-tokens 64000 \\
|
--n-repeats 16 --max-tokens 64000 \\
|
||||||
--temperature 1.0 --top-p 0.95 --thinking \\
|
--temperature 1.0 --top-p 0.95 --thinking \\
|
||||||
@@ -79,6 +87,7 @@ sgl-eval run aime26 \\
|
|||||||
|
|
||||||
accuracyLabels: [
|
accuracyLabels: [
|
||||||
["aime26_pct", "AIME26", "%"],
|
["aime26_pct", "AIME26", "%"],
|
||||||
|
["aime25_pct", "AIME25", "%"],
|
||||||
["gsm8k_pct", "GSM8K (1-shot)", "%"],
|
["gsm8k_pct", "GSM8K (1-shot)", "%"],
|
||||||
],
|
],
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user