llamamodel: add missing softmax to fix temperature (#3202)

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel 2024-12-04 10:56:19 -05:00 committed by GitHub
parent ffd29eae08
commit 0c70b5a5f4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 1 deletions

View File

@ -584,7 +584,8 @@ void LLamaModel::initSampler(const PromptContext &promptCtx)
llama_sampler_init_top_p(promptCtx.top_p, 1), llama_sampler_init_top_p(promptCtx.top_p, 1),
llama_sampler_init_min_p(promptCtx.min_p, 1), llama_sampler_init_min_p(promptCtx.min_p, 1),
llama_sampler_init_temp(promptCtx.temp), llama_sampler_init_temp(promptCtx.temp),
llama_sampler_init_dist(LLAMA_DEFAULT_SEED) llama_sampler_init_softmax(),
llama_sampler_init_dist(LLAMA_DEFAULT_SEED),
}; };
for (auto *smpl : samplers) for (auto *smpl : samplers)
llama_sampler_chain_add(chain, smpl); llama_sampler_chain_add(chain, smpl);

View File

@ -17,6 +17,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
### Fixed ### Fixed
- Fix bug in GUI when localdocs encounters binary data ([#3137](https://github.com/nomic-ai/gpt4all/pull/3137)) - Fix bug in GUI when localdocs encounters binary data ([#3137](https://github.com/nomic-ai/gpt4all/pull/3137))
- Fix LocalDocs bugs that prevented some docx files from fully chunking ([#3140](https://github.com/nomic-ai/gpt4all/pull/3140)) - Fix LocalDocs bugs that prevented some docx files from fully chunking ([#3140](https://github.com/nomic-ai/gpt4all/pull/3140))
- Fix missing softmax that was causing crashes and effectively infinite temperature since 3.4.0 ([#3202](https://github.com/nomic-ai/gpt4all/pull/3202))
## [3.4.2] - 2024-10-16 ## [3.4.2] - 2024-10-16