lakomoor/
vikhr-llama-3.2-1b-instruct:q2_k

2,545 1 year ago

Instructive model based on Llama-3.2-1B-Instruct, trained on the Russian-language dataset GrandMaster-PRO-MAX. It is 5 times more efficient than the base model, making it perfect for deployment on low-power or mobile devices.

1b
... /
params
737905d4663d · 161B
{
"num_ctx": 4096,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>",
"<|reserved_special_token"
],
"temperature": 0.2
}