Trained through RLHF based off Llama-3-70B-Instruct, high scores on Arena-Hard-Auto.
386 Pulls Updated 3 months ago
577073ffcc6c · 110B
{
"num_keep": 24,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}