Files
OpenSonnet-Lite-MAX/.eval_results/gsm8k.yaml

24 lines
526 B
YAML
Raw Normal View History

- dataset:
id: openai/gsm8k
task_id: gsm8k
value: 85.22
date: "2026-05-10"
source:
url: https://huggingface.co/hadadxyz/OpenSonnet-Lite-MAX
name: Model Card
user: hadadxyz
notes: |
framework: lm-evaluation-harness
n-shot: 8
batch_size: 1
generation_kwargs:
num_ctx: 262144
max_tokens: 131072
temperature: 0.6
top_p: 0.95
top_k: 20
min_p: 0
repeat_penalty: 1.0
presence_penalty: 1.0
metric: exact_match
match_type: strict-match