This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-70B-Instruct.
70B
487 Pulls Updated 4 months ago
11 Tags
ad9579e5734e • 43GB •
Updated 4 months ago
Q4_K_M
latest
ad9579e5734e • 43GB •
Updated 4 months ago
a05eb0e9a72b • 282GB •
Updated 4 months ago
d6b40dce253a • 26GB •
Updated 4 months ago
f4d96e27f090 • 31GB •
Updated 4 months ago
2e1b19eb5137 • 34GB •
Updated 4 months ago
1c54d8aea32a • 37GB •
Updated 4 months ago
e580b7cae026 • 40GB •
Updated 4 months ago
7b5249fb809d • 49GB •
Updated 4 months ago
3c3354de6304 • 50GB •
Updated 4 months ago
3abcd2574a85 • 58GB •
Updated 4 months ago