mannix/
smaug-llama3-70b

262 1 year ago

This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct

9 models

smaug-llama3-70b:latest
213da162e11c • 40GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:q3_k_s
b4cef5c79835 • 31GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:q4_0
213da162e11c • 40GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:q4_k_m
8ee9c33bcfe6 • 43GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:q5_k_m
ccbf9420812e • 50GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:q6_k
a55280cbe23b • 58GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:iq2_xs
42a8a42a1bc5 • 21GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:iq3_xxs
e7910dd061a6 • 27GB • 8K context window •
Text input • 1 year ago
smaug-llama3-70b:iq3_s
5620366a6465 • 31GB • 8K context window •
Text input • 1 year ago