Dual Gpo 15 indexed models
15 matching models
huggingface/DUAL-GPO/phi-2-dpo-renew1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 62.772% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-0.5ultrafeedback-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 61.213% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-0.5ultrafeedback-lowLr-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 61.356% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-extra-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 61.495% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-i0
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 63.48% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-log-i0
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 63.329% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-v4-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 61.336% huggingface/DUAL-GPO/phi-2-gpo-renew2-b0.001-vllm-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 61.319% huggingface/DUAL-GPO/zephyr-7b-dpo-qlora-v1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 64.432% huggingface/DUAL-GPO/zephyr-7b-gpo-update3-i0
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 63.314% huggingface/DUAL-GPO/zephyr-7b-gpo-update4-i0
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 63.173% huggingface/DUAL-GPO/zephyr-7b-gpo-v5-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 62.682% huggingface/DUAL-GPO/zephyr-7b-ipo-0k-15k-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 15.493% huggingface/DUAL-GPO/zephyr-7b-ipo-qlora-v0
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 62.665% huggingface/DUAL-GPO/zephyr-7b-lgpo-v1-i1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 62.538%
EVIDENCE / COMPARISON
Benchmarks
Explore every benchmark
Loading
Search evaluations
Dimension
All dimensions
Source
All sources
Entries
Top 12
Top 25
Top 50
These charts contain model-linked results. The charts
above also include unlinked source profiles. Compare
scores within each evaluation. Model quality, usage,
transparency and system performance measure different
things.