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

2,543 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

8 models

vikhr-llama-3.2-1b-instruct:1b
a27385402253 • 771MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:q2_k
f8d31ac19fc4 • 581MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:q3_k_m
4f1914405434 • 691MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:q4_0
a27385402253 • 771MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:q5_k_m
2103620d3a69 • 912MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:q6_k
99b5474feef2 • 1.0GB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:iq1_s
507dbbca4ebd • 394MB • 128K context window •
Text input • 1 year ago
vikhr-llama-3.2-1b-instruct:fp16
acbf9b910717 • 2.5GB • 128K context window •
Text input • 1 year ago