- Mistral-7B-capybara-v0.1
- Mistral-7B-capybara-v0.2
- Mistral-7B-capybara-v0.3
- Mistral-7B-v0.1-ORPO-Capybara-TRL-w-pl
- Mistral-7B-v0.1-ORPO-Capybara-TRL-wo-pl
- Mistral-7B-v0.1-ORPO-Capybara-TRL
- Mixtral-8x22B-capybara-v0.1
- Mixtral-8x22B-capybara-v0.2
- Mixtral-8x22B-capybara-v0.3
- Mixtral-8x7B-capybara-dpo-7k-v0.1
- Qwen1.5-0.5B-capybara-dpo-7k-v0.1
- Qwen1.5-14B-ORPO-Capybara-7k
- Qwen1.5-72B-capybara-dpo-7k-v0.1
- Qwen1.5-7B-ORPO-Capybara-7k
- Qwen1.5-7B-ohp-100k-v0.1
- Qwen1.5-7B-ohp-10k-Beta0.2-v0.1
- Qwen1.5-7B-ohp-10k-Beta0.25-v0.1
- Qwen1.5-7B-ohp-10k-v0.1
- Qwen1.5-7B-ohp-10k-v0.10
- Qwen1.5-7B-ohp-10k-v0.11
- Qwen1.5-7B-ohp-10k-v0.12
- Qwen1.5-7B-ohp-10k-v0.13
- Qwen1.5-7B-ohp-10k-v0.14
- Qwen1.5-7B-ohp-10k-v0.15
- Qwen1.5-7B-ohp-10k-v0.2
- Qwen1.5-7B-ohp-10k-v0.3
- Qwen1.5-7B-ohp-10k-v0.5
- Qwen1.5-7B-ohp-10k-v0.6
- Qwen1.5-7B-ohp-10k-v0.7
- Qwen1.5-7B-ohp-10k-v0.8
- Qwen1.5-7B-ohp-10k-v0.9
- Qwen1.5-7B-ohp-250k-v0.1
- Qwen1.5-7B-ohp-25k-v0.1
- Qwen1.5-7B-ohp-500k-v0.1
- Qwen1.5-7B-ohp-50k-v0.1
- Qwen1.5-7B-ohp-all-v0.1
- argilla-mistral-orpo-OHP-15k-Stratified-1-2-3-beta-0.2-epoch-3
- argilla-mistral-orpo-OHP-15k-Stratified-3-beta-0.2-epoch-1
- argilla-mistral-orpo-OpenHermesPreferences-100k-beta-0.2-ckpt-epoch-1
- argilla-mistral-orpo-OpenHermesPreferences-100k-beta-0.2-ckpt-epoch-2
- argilla-mistral-orpo-OpenHermesPreferences-100k-beta-0.2
- argilla-mistral-orpo-OpenHermesPreferences-50k-beta-0.2-ckpt-epoch-1
- argilla-mistral-orpo-OpenHermesPreferences-50k-beta-0.2-ckpt-epoch-2
- argilla-mistral-orpo-OpenHermesPreferences-50k-beta-0.2
- argilla-mistral-orpo-capybara-beta-0.05-iter-1-ckpt-1
- argilla-mistral-orpo-capybara-beta-0.05-iter-1-ckpt-2
- argilla-mistral-orpo-capybara-beta-0.05-iter-1
- hf-llama3-70b-orpo-CapybaraPreferences-bs-128
- hf-llama3-70b-orpo-CapybaraPreferences-bs-256
- hf-llama3-70b-orpo-CapybaraPreferences-bs-512