SaylorTwift/harbor-traces
10.7 MB
Nathan Habib PRO
SaylorTwift
AI & ML interests
Evals
Recent Activity
liked a Space about 1 hour ago
huggingface/how-to-upgrade-to-enterprise updated a bucket about 2 hours ago
SaylorTwift/benchflow-dummy-test upvoted an article about 2 hours ago
Measuring benchmark optimization in speech recognitionOrganizations
Posts 1
Post
3127
How do I test an LLM for my unique needs?
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.
https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.
https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md
Articles 14
Article
52
Featuring Every Eval Ever Results on Hugging Face Model Pages
spaces 26
Running
3
Benchmark Holo Deck
🌈
Explore LLM benchmarks with visual rarity cards
Sleeping
Agents
LLM Benchmark Usage Explorer
📊
Explore LLM benchmark usage across models and labs
Sleeping
MCP
Reposcan
🦀
Search and explore repo issues, PRs, and code
Running
Qwen3 8B
📉
Inspect and browse server log files
Running
Qwen2.5 0.5B Instruct Evals
📊
Inspect and view log files in a web interface
Running
Meta Llama 3.1 8b Cb
📉
Inspect and explore log files in a web view
datasets 58
SaylorTwift/llm-benchmark-usage
Viewer • Updated • 306 • 277 • 1
SaylorTwift/harbor-assets
Updated • 11
SaylorTwift/gemma4-blog-images
Viewer • Updated • 1 • 16
SaylorTwift/mteb-bitext-mining-aggregated
Viewer • Updated • 588k • 615
SaylorTwift/gsm8k-cb-llama31-8b-results
Viewer • Updated • 100 • 26
SaylorTwift/gsm8k-cb-results
Viewer • Updated • 100 • 16
SaylorTwift/aime-2026-qwen35-results
Viewer • Updated • 1 • 20
SaylorTwift/aime-2026-qwen25-72b-results
Viewer • Updated • 1 • 22
SaylorTwift/aime-2026-vllm-results
Viewer • Updated • 1 • 33
SaylorTwift/claude-sonnet-4-0
Updated • 77