This model extends LLama-3 8B's context length from 8k to over 1m tokens.
8b
70b
91.2K Pulls Updated 6 months ago
577073ffcc6c · 110B
{
"num_keep": 24,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}