Meta Llama-3-8b with Self-Play Preference Optimization for Language Model Alignment at iteration 3
186 Pulls Updated 4 months ago
577073ffcc6c · 110B
{
"num_keep": 24,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}