From c950fdd84e31757d5f832acae9d483d6c4f101d1 Mon Sep 17 00:00:00 2001 From: Jared Van Bortel Date: Wed, 7 Aug 2024 18:59:57 -0400 Subject: [PATCH] changelogs: add PR 2781 (#2809) Signed-off-by: Jared Van Bortel --- gpt4all-bindings/python/CHANGELOG.md | 5 +++++ gpt4all-chat/CHANGELOG.md | 4 ++++ 2 files changed, 9 insertions(+) diff --git a/gpt4all-bindings/python/CHANGELOG.md b/gpt4all-bindings/python/CHANGELOG.md index 20c8eece..2e5be01f 100644 --- a/gpt4all-bindings/python/CHANGELOG.md +++ b/gpt4all-bindings/python/CHANGELOG.md @@ -9,6 +9,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). ### Changed - Search for pip-installed CUDA 11 as well as CUDA 12 ([#2802](https://github.com/nomic-ai/gpt4all/pull/2802)) - Stop shipping CUBINs to reduce wheel size ([#2802](https://github.com/nomic-ai/gpt4all/pull/2802)) +- Use llama\_kv\_cache ops to shift context faster ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) +- Don't stop generating at end of context ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) + +### Fixed +- Make reverse prompt detection work more reliably and prevent it from breaking output ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) ## [2.8.0] - 2024-08-05 diff --git a/gpt4all-chat/CHANGELOG.md b/gpt4all-chat/CHANGELOG.md index 114320a7..4084b4a0 100644 --- a/gpt4all-chat/CHANGELOG.md +++ b/gpt4all-chat/CHANGELOG.md @@ -11,6 +11,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). ### Changed - Add missing entries to Italian transltation (by [@Harvester62](https://github.com/Harvester62) in [#2783](https://github.com/nomic-ai/gpt4all/pull/2783)) +- Use llama\_kv\_cache ops to shift context faster ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) +- Don't stop generating at end of context ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) ### Fixed - Case-insensitive LocalDocs source icon detection (by [@cosmic-snow](https://github.com/cosmic-snow) in [#2761](https://github.com/nomic-ai/gpt4all/pull/2761)) @@ -18,6 +20,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). - Fix several backend issues ([#2778](https://github.com/nomic-ai/gpt4all/pull/2778)) - Restore leading space removal logic that was incorrectly removed in [#2694](https://github.com/nomic-ai/gpt4all/pull/2694) - CUDA: Cherry-pick llama.cpp DMMV cols requirement fix that caused a crash with long conversations since [#2694](https://github.com/nomic-ai/gpt4all/pull/2694) +- Make reverse prompt detection work more reliably and prevent it from breaking output ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) +- Disallow context shift for chat name and follow-up generation to prevent bugs ([#2781](https://github.com/nomic-ai/gpt4all/pull/2781)) ## [3.1.1] - 2024-07-27