github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-10 12:59:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Whitelist OLMoE and Granite MoE (#3449)

Browse Source 
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
ThiloteE
2025-02-05 00:00:07 +01:00
committed by GitHub
parent 04dc157b98
commit 6ef0bd518e
3 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-backend/deps/llama.cpp-mainline

Submodule gpt4all-backend/deps/llama.cpp-mainline updated: b06658d366...3ebb3603e8

2
gpt4all-backend/src/llamamodel.cpp
View File

@@ -53,6 +53,7 @@ static const std::vector<const char *> KNOWN_ARCHES {
"gpt2", "gpt2",
// "gptj", -- no inference code // "gptj", -- no inference code
"gptneox", "gptneox",
"granitemoe",
"mpt", "mpt",
"baichuan", "baichuan",
"starcoder", "starcoder",
@@ -80,6 +81,7 @@ static const std::vector<const char *> KNOWN_ARCHES {
"command-r", "command-r",
// "dbrx", -- 16x12B parameters // "dbrx", -- 16x12B parameters
"olmo", "olmo",
"olmoe",
"openelm", "openelm",
// "arctic", -- 10B+128x3.66B parameters // "arctic", -- 10B+128x3.66B parameters
"deepseek2", "deepseek2",

3
gpt4all-chat/CHANGELOG.md
View File

@@ -6,6 +6,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
## [Unreleased] ## [Unreleased]
### Added
- Whitelist OLMoE and Granite MoE model architectures (no Vulkan) ([#3449](https://github.com/nomic-ai/gpt4all/pull/3449))
### Fixed ### Fixed
- Fix "index N is not a prompt" when using LocalDocs with reasoning ([#3451](https://github.com/nomic-ai/gpt4all/pull/3451) - Fix "index N is not a prompt" when using LocalDocs with reasoning ([#3451](https://github.com/nomic-ai/gpt4all/pull/3451)
- Work around rendering artifacts on Snapdragon SoCs with Windows ([#3450](https://github.com/nomic-ai/gpt4all/pull/3450)) - Work around rendering artifacts on Snapdragon SoCs with Windows ([#3450](https://github.com/nomic-ai/gpt4all/pull/3450))