llama.cpp
Add Command R Plus support
#6491
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
15
Changes
View On
GitHub
Add Command R Plus support
#6491
ggerganov
merged 15 commits into
ggml-org:master
from
RefractAI:master
Add Command R Plus GGUF
2efcd87b
Add Command R Plus GGUF
fbab9849
Loading works up to LayerNorm2D
e4b2e2d3
Export new tensors in 1D so they are not quantized.
c354db75
RefractAI
marked this pull request as draft
2 years ago
Fix embedding layer based on Noeda's example
553b09ba
Whitespace
f3532ff8
RefractAI
marked this pull request as ready for review
2 years ago
Add line
ec613b85
Fix unexpected tokens on MPS. Re-add F16 fix. ((Noeda)
c2658c3a
dranger003: Fix block index overflow in CUDA dequantizing.
6745ea7a
slaren
commented on 2024-04-06
Reverted blocked multiplication code as it still has issues and could…
26e8f23b
export norms as f32
ce9413d8
fix overflow issues during quant and other cleanup
78819c07
Merge pull request #1 from slaren/cmrp-fixes
8b6577bd
zsqdx
approved these changes on 2024-04-07
slaren
approved these changes on 2024-04-07
slaren
requested a review
from
ggerganov
2 years ago
ggerganov
approved these changes on 2024-04-07
Type convention
d2924073
sammcj
approved these changes on 2024-04-08
dranger003: Fix more int overflow during quant.
ea1aeba4
ggerganov
merged
5dc9dd71
into master
2 years ago
phymbert
commented on 2024-04-09
phymbert
commented on 2024-04-09
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
slaren
sammcj
zsqdx
dranger003
phymbert
Noeda
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub