princeton-nlp/warm-start__sft__think__Llama-3.1-8B-Instruct
8B
•
Updated
•
15
RLMT Experiments
The *RLMT* collection. Coming soon!
-
-
princeton-nlp/warm-start__sft__nothink__Qwen2.5-7B-Instruct
8B • Updated • 18 -
princeton-nlp/warm-start__sft__think__Llama-3.1-8B
8B • Updated • 18 -
princeton-nlp/warm-start__sft__think__Qwen2.5-7B
8B • Updated • 15 -
princeton-nlp/warm-start__sft__nothink__Llama-3.1-8B-Instruct
8B • Updated • 19 -
princeton-nlp/warm-start__sft__think__Qwen2.5-7B-Instruct
8B • Updated • 17 -
princeton-nlp/warm-start__sft__nothink__Llama-3.1-8B
8B • Updated • 13 -
princeton-nlp/warm-start__sft__nothink__Qwen2.5-7B
8B • Updated • 21 -
princeton-nlp/warm-start__dpo__think__Llama-3.1-8B
8B • Updated • 18 -
princeton-nlp/warm-start__dpo__think__Qwen2.5-7B
8B • Updated • 18 -
princeton-nlp/warm-start__dpo__think__Llama-3.1-8B-Instruct
8B • Updated • 17 -
princeton-nlp/warm-start__dpo__think__Qwen2.5-7B-Instruct
8B • Updated • 17 -
princeton-nlp/warm-start__dpo__nothink__Llama-3.1-8B
8B • Updated • 16 -
princeton-nlp/warm-start__dpo__nothink__Qwen2.5-7B
8B • Updated • 15 -
princeton-nlp/warm-start__dpo__nothink__Llama-3.1-8B-Instruct
8B • Updated • 14 -
princeton-nlp/warm-start__dpo__nothink__Qwen2.5-7B-Instruct
8B • Updated • 13 -
princeton-nlp/warm-start__ppo__think__Qwen2.5-7B
8B • Updated • 18 -
princeton-nlp/warm-start__ppo__think__Llama-3.1-8B-Instruct
8B • Updated • 17 -
princeton-nlp/warm-start__ppo__think__Qwen2.5-7B-Instruct
8B • Updated • 23 -
princeton-nlp/warm-start__ppo__nothink__Llama-3.1-8B
8B • Updated • 15 -
princeton-nlp/warm-start__ppo__nothink__Qwen2.5-7B
8B • Updated • 15 -
princeton-nlp/warm-start__ppo__nothink__Llama-3.1-8B-Instruct
8B • Updated • 19 -
princeton-nlp/warm-start__ppo__nothink__Qwen2.5-7B-Instruct
8B • Updated • 17 -
princeton-nlp/zero__base__think__Llama-3.1-8B
8B • Updated • 17 -
princeton-nlp/zero__base__nothink__Llama-3.1-8B
8B • Updated • 18 -
princeton-nlp/zero__base__think__Qwen2.5-7B
8B • Updated • 15 -
princeton-nlp/zero__base__nothink__Qwen2.5-7B
8B • Updated • 14 -
princeton-nlp/zero__dpo__think__Llama-3.1-8B
8B • Updated • 14 -
princeton-nlp/zero__dpo__think__Qwen2.5-7B
8B • Updated • 17 -
princeton-nlp/zero__dpo__nothink__Llama-3.1-8B
8B • Updated • 17 -
princeton-nlp/zero__dpo__nothink__Qwen2.5-7B
8B • Updated • 14 -
princeton-nlp/zero__ppo__think__Llama-3.1-8B
8B • Updated • 17 -
princeton-nlp/zero__ppo__think__Qwen2.5-7B
8B • Updated • 16 -
princeton-nlp/warm-start__ppo__think__Llama-3.1-8B
8B • Updated • 21 -
princeton-nlp/zero__ppo__nothink__Qwen2.5-7B
8B • Updated • 13 -
princeton-nlp/zero__grpo__think__Llama-3.1-8B
8B • Updated • 19 -
princeton-nlp/zero__grpo__think__Qwen2.5-7B
8B • Updated • 18 -
princeton-nlp/zero__grpo__nothink__Llama-3.1-8B
8B • Updated • 16 -
princeton-nlp/zero__grpo__nothink__Qwen2.5-7B
8B • Updated • 16 -
princeton-nlp/rl_tulu3_wildchat-if_prompts
Viewer • Updated • 7.79k • 114 • 1 -
princeton-nlp/gemini_2.5_flash_0417_sft-data
Viewer • Updated • 6k • 115 -
princeton-nlp/warm-start__grpo__nothink__Qwen2.5-7B-Instruct
8B • Updated • 18 -
princeton-nlp/warm-start__grpo__nothink__Llama-3.1-8B-Instruct
8B • Updated • 17 -
princeton-nlp/warm-start__grpo__nothink__Qwen2.5-7B
8B • Updated • 13 -
princeton-nlp/warm-start__grpo__nothink__Llama-3.1-8B
8B • Updated • 16 -
princeton-nlp/warm-start__grpo__think__Qwen2.5-7B-Instruct
8B • Updated • 20 -
princeton-nlp/warm-start__grpo__think__Llama-3.1-8B-Instruct
8B • Updated • 28 -
princeton-nlp/warm-start__grpo__think__Qwen2.5-7B
8B • Updated • 17 -
princeton-nlp/warm-start__grpo__think__Llama-3.1-8B
8B • Updated • 16