-
Notifications
You must be signed in to change notification settings - Fork 9.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add Command R Plus support #6491
Commits on Apr 4, 2024
-
S authored and S committed
Apr 4, 2024 Configuration menu - View commit details
-
Copy full SHA for 2efcd87 - Browse repository at this point
Copy the full SHA 2efcd87View commit details -
S authored and S committed
Apr 4, 2024 Configuration menu - View commit details
-
Copy full SHA for fbab984 - Browse repository at this point
Copy the full SHA fbab984View commit details -
Loading works up to LayerNorm2D
S authored and S committedApr 4, 2024 Configuration menu - View commit details
-
Copy full SHA for e4b2e2d - Browse repository at this point
Copy the full SHA e4b2e2dView commit details -
Export new tensors in 1D so they are not quantized.
S committedApr 4, 2024 Configuration menu - View commit details
-
Copy full SHA for c354db7 - Browse repository at this point
Copy the full SHA c354db7View commit details
Commits on Apr 5, 2024
-
Fix embedding layer based on Noeda's example
S committedApr 5, 2024 Configuration menu - View commit details
-
Copy full SHA for 553b09b - Browse repository at this point
Copy the full SHA 553b09bView commit details -
S committed
Apr 5, 2024 Configuration menu - View commit details
-
Copy full SHA for f3532ff - Browse repository at this point
Copy the full SHA f3532ffView commit details -
S committed
Apr 5, 2024 Configuration menu - View commit details
-
Copy full SHA for ec613b8 - Browse repository at this point
Copy the full SHA ec613b8View commit details
Commits on Apr 6, 2024
-
Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)
S committedApr 6, 2024 Configuration menu - View commit details
-
Copy full SHA for c2658c3 - Browse repository at this point
Copy the full SHA c2658c3View commit details -
dranger003: Fix block index overflow in CUDA dequantizing.
S committedApr 6, 2024 Configuration menu - View commit details
-
Copy full SHA for 6745ea7 - Browse repository at this point
Copy the full SHA 6745ea7View commit details -
Reverted blocked multiplication code as it still has issues and could…
… affect other Llama arches
S committedApr 6, 2024 Configuration menu - View commit details
-
Copy full SHA for 26e8f23 - Browse repository at this point
Copy the full SHA 26e8f23View commit details -
Configuration menu - View commit details
-
Copy full SHA for ce9413d - Browse repository at this point
Copy the full SHA ce9413dView commit details -
Configuration menu - View commit details
-
Copy full SHA for 78819c0 - Browse repository at this point
Copy the full SHA 78819c0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8b6577b - Browse repository at this point
Copy the full SHA 8b6577bView commit details
Commits on Apr 7, 2024
-
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for d292407 - Browse repository at this point
Copy the full SHA d292407View commit details
Commits on Apr 8, 2024
-
dranger003: Fix more int overflow during quant.
S committedApr 8, 2024 Configuration menu - View commit details
-
Copy full SHA for ea1aeba - Browse repository at this point
Copy the full SHA ea1aebaView commit details