- 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
- hf-llama3-8b-orpo-v0.0
- kaist-llama3-8b-orpo-OpenHermesPreferences-v2.0
- kaist-llama3-8b-orpo-capybara-preferences-v2.0
- kaist-llama3-8b-orpo-ultrainteract-v2.0
- kaist-mistral-orpo-OHP-15k-Mathcode-1epoch-ohp-15k-strat-1-2epoch
- kaist-mistral-orpo-OHP-15k-Mathcode-2epoch-ohp-15k-strat-1-1epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.05-1epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.05
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.1
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch-capybara-2epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch-math-2epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch-capybara-1epoch
- kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch-math-1epoch