Skip to content

Update README.md #5366

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Feb 6, 2024
+13 −1
Merged

Update README.md #5366

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -736,9 +736,21 @@ Several quantization methods are supported. They differ in the resulting model d
| 13B | bits/weight | 16.0 | 4.5 | 5.0 | 5.5 | 6.0 | 8.5 |

- [k-quants](https://github.com/ggerganov/llama.cpp/pull/1684)
- recent k-quants improvements
- recent k-quants improvements and new i-quants
- [#2707](https://github.com/ggerganov/llama.cpp/pull/2707)
- [#2807](https://github.com/ggerganov/llama.cpp/pull/2807)
- [#4773 - 2-bit i-quants (inference)](https://github.com/ggerganov/llama.cpp/pull/4773)
- [#4856 - 2-bit i-quants (inference)](https://github.com/ggerganov/llama.cpp/pull/4856)
- [#4861 - importance matrix](https://github.com/ggerganov/llama.cpp/pull/4861)
- [#4872 - MoE models](https://github.com/ggerganov/llama.cpp/pull/4872)
- [#4897 - 2-bit quantization](https://github.com/ggerganov/llama.cpp/pull/4897)
- [#4930 - imatrix for all k-quants](https://github.com/ggerganov/llama.cpp/pull/4930)
- [#4951 - imatrix on the GPU](https://github.com/ggerganov/llama.cpp/pull/4957)
- [#4969 - imatrix for legacy quants](https://github.com/ggerganov/llama.cpp/pull/4969)
- [#4996 - k-qunats tuning](https://github.com/ggerganov/llama.cpp/pull/4996)
- [#5060 - Q3_K_XS](https://github.com/ggerganov/llama.cpp/pull/5060)
- [#5196 - 3-bit i-quants](https://github.com/ggerganov/llama.cpp/pull/5196)
- [quantization tuning](https://github.com/ggerganov/llama.cpp/pull/5320), [another one](https://github.com/ggerganov/llama.cpp/pull/5334), and [another one](https://github.com/ggerganov/llama.cpp/pull/5361)

### Perplexity (measuring model quality)

Expand Down