Ewqr2130 17 indexed models
17 matching models
huggingface/ewqr2130/7B_ppo_phiRM_2GPU_3e-7step_4000
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 57.463% huggingface/ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 58.368% huggingface/ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 58.587% huggingface/ewqr2130/alignment-handbook-zephyr-7b_ppostep_100
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 0% huggingface/ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 58.293% huggingface/ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 58.669% huggingface/ewqr2130/llama2-7b-raw-sft
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 45.675% huggingface/ewqr2130/llama2-ppo
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 39.442% huggingface/ewqr2130/llama_ppo_1e6_new_tokenizerstep_8000
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 51.667% huggingface/ewqr2130/llama_ppo_1e6step_4000
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 51.612% huggingface/ewqr2130/llama_sft_longer
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 51.642% huggingface/ewqr2130/mistral-7b-raw-sft
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 45.675% huggingface/ewqr2130/mistral-inst-ppo
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 63.793% huggingface/ewqr2130/mistral-inst-v02-dpo
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 30.426% huggingface/ewqr2130/mistral-moe-scratch
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 0% huggingface/ewqr2130/mistral-se-inst-ppo
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 55.298% huggingface/ewqr2130/TinyLamma-SFT
Input modalities text
Output modalities text Benchmarks Open LLM Leaderboard v1: 35.883%
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.