itzune/ latxa:8b

38 5 months ago

Latxa is based on Llama-3.1, which is trained on a Basque corpus comprising 4.3M documents and 4.2B tokens using language adaptation techniques.

tools 8b
... /
params
56bb8bd477a5 · 96B
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}