Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
abhshkp
/
litm-benchmark-suite-v4
like
0
ml-intern
lost-in-the-middle
long-context
position-bias
benchmark
arxiv:
2307.03172
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
litm-benchmark-suite-v4
162 kB
Ctrl+K
Ctrl+K
1 contributor
History:
84 commits
abhshkp
Fix scoring bug in Exp 4: check all numbers for expected answer, not just first number
3e790f1
verified
7 days ago
experiments
Fix scoring bug in Exp 4: check all numbers for expected answer, not just first number
7 days ago
kaggle
Add multi-model comparative runner with Mistral as default
7 days ago
src
Add Curve Shape Classifier (CSC) + enhanced metrics
7 days ago
.gitattributes
Safe
1.52 kB
initial commit
17 days ago
README.md
Safe
28.5 kB
Upload README.md
16 days ago
analyze_taxonomy.py
Safe
10.5 kB
Add taxonomy analysis script with shape gallery, PBI charts, LaTeX tables
7 days ago
config.yaml
Safe
1.66 kB
Change default model to Mistral-7B-Instruct-v0.3
7 days ago
paper_latex_template.tex
Safe
16.3 kB
Add full LaTeX paper template with Mistral included in model list
7 days ago
requirements.txt
Safe
105 Bytes
Upload requirements.txt
17 days ago
run_all.py
Safe
6.16 kB
Change default model to Mistral-7B-Instruct-v0.3
7 days ago