A collection of reasoning tasks to benchmark model abilities
Sara Candussio
saracandu
AI & ML interests
Reasoning in Large Language Models
Recent Activity
updated
a model
about 1 hour ago
saracandu/stlenc-distilled-v2
updated
a model
about 2 hours ago
saracandu/stlenc-distilled
updated
a model
about 2 hours ago
saracandu/stlenc-distilled-v2
Organizations
models
24
saracandu/stlenc-distilled-v2
0.2B
•
Updated
•
46
saracandu/stlenc-distilled
0.2B
•
Updated
•
297
saracandu/stlenc
Feature Extraction
•
0.2B
•
Updated
•
635
saracandu/stldec_onlyhard
Text Generation
•
0.2B
•
Updated
•
3
saracandu/stldec_random_1024_pca
Text Generation
•
0.2B
•
Updated
•
3
saracandu/stldec_random_128_umap
Text Generation
•
14.4M
•
Updated
•
2
saracandu/stldec_random_64_umap
Text Generation
•
6.81M
•
Updated
•
1
saracandu/stldec_random_32_umap
Text Generation
•
3.33M
•
Updated
•
2
saracandu/stldec_random_16_umap
Text Generation
•
1.66M
•
Updated
•
3
saracandu/stldec_random_512_pca
Text Generation
•
76.1M
•
Updated
•
2
datasets
9
saracandu/stl_formulae_variants
Viewer
•
Updated
•
510k
•
65
saracandu/smol_reas_traces
Viewer
•
Updated
•
36k
•
37
•
1
saracandu/implications
Viewer
•
Updated
•
19.9k
•
31
saracandu/stl_formulae_umap
Viewer
•
Updated
•
81.9k
•
4
saracandu/stl_formulae
Viewer
•
Updated
•
81.9k
•
114
saracandu/eureka-rebus-primalettura
Viewer
•
Updated
•
83.1k
•
6
saracandu/eureka-rebus-grpo
Viewer
•
Updated
•
83.1k
•
11
saracandu/rebus-grpo-reasoning
Viewer
•
Updated
•
180
•
6
saracandu/filtered_hotpotQA
Viewer
•
Updated
•
352
•
31
•
1