LLM customized by NVIDIA to improve the helpfulness of generated responses #1 on all three automatic alignment benchmarks (verified tab for AlpacaEval 2 LC), edging out strong frontier models such as GPT-4o and Claude 3.5 Sonnet.
70B
41 Pulls Updated 4 hours ago
b886668057ed · 111B
{
"num_ctx": 5120,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}