Jayhyeon 174 indexed models
174 matching models
huggingface/JayHyeon/Qwen-0.5B-DPO-1epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.386% huggingface/JayHyeon/Qwen-0.5B-DPO-5epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.199% huggingface/JayHyeon/Qwen-0.5B-eDPO-1epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.281% huggingface/JayHyeon/Qwen-0.5B-eDPO-5epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 6.728% huggingface/JayHyeon/Qwen-0.5B-IRPO-1epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.032% huggingface/JayHyeon/Qwen-0.5B-IRPO-5epoch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 6.923% huggingface/JayHyeon/Qwen_0.5-cDPO_5e-7-3ep_0vpo_const_0.1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.905% huggingface/JayHyeon/Qwen_0.5-cDPO_5e-7-3ep_0vpo_const_0.3
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.98% huggingface/JayHyeon/Qwen_0.5-DPO_1e-6-3ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.627% huggingface/JayHyeon/Qwen_0.5-DPO_1e-7-3ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.573% huggingface/JayHyeon/Qwen_0.5-DPO_3e-6-1ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 6.92% huggingface/JayHyeon/Qwen_0.5-DPO_3e-6-2ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 8.076% huggingface/JayHyeon/Qwen_0.5-DPO_3e-6-3ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.643% huggingface/JayHyeon/Qwen_0.5-DPO_3e-7-1ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.97% huggingface/JayHyeon/Qwen_0.5-DPO_3e-7-2ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.961% huggingface/JayHyeon/Qwen_0.5-DPO_3e-7-3ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 7.741% huggingface/JayHyeon/Qwen_0.5-DPO_5e-7-1ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 8.082% huggingface/JayHyeon/Qwen_0.5-DPO_5e-7-2ep_0alp_0lam
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v2: 8.095%
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.