llama.cpp commit e3c337d87 ("llama : support negative ith in llama_get_
API (#6519)") added a simpler way to get the logits for the last token
in the batch, so use that instead. This also fixes potential issues with
not serializing this value with the rest of the prompt context, although
in practice we should always call evalTokens before
llama_sample_top_p_top_k.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
When llama.cpp was updated, I removed the space removal logic, but it
turns out it's still actually needed. This is now a proper parameter, as
we specifically only want to disable the *leading* space when we are
tokenizing input that comes after a normal token.
This fixes a regression in commit 290c6294 ("backend: rebase llama.cpp
submodule on latest upstream (#2694)").
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
The size of the token cache is expected to match n_past during the
decode phase of llmodel_prompt. We should make sure they match at entry,
and never do anything that could cause them to desync.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Since upstream commit 1b67731e1 ("BERT tokenizer fixes (#6498)"),
llama_tokenize will not add BOS for tokenizers that should not have it.
Since upstream commit 37bef8943 ("tokenizer : BPE fixes (#7530)"),
llama_add_bos_token can be used to confidently determine whether BOS
will be added by llama_tokenize.
The upstream logic to determine whether to add BOS has grown as
tokenizers have been added and improved, so this could fix problems with
a missing BOS, or context recalculation preserving the first token when
it shouldn't.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Pre-release and post-release suffixes are now interpreted correctly. Also fix comparison of incomplete versions.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Minor, cosmetic fix to the file icon which is shown as a LocalDocs source.
A recent commit has allowed the file suffixes to be mixed case, this makes the
displayed icon consistent, so that e.g. '.PDF' is uses the right icon, as well.
Signed-off-by: Cosmic Snow <cosmic-snow@mailfence.com>
- Added maintainer for the flatpak
- Update screenshots
- Remove the mentioning of gpt-j model support
- Removed the flatpak manifest, the current version is here https://github.com/flathub/io.gpt4all.gpt4all
Signed-off-by: Tim <tim453@mailbox.org>
Signed-off-by: AT <manyoso@users.noreply.github.com>
Co-authored-by: AT <manyoso@users.noreply.github.com>
- updates features
- removes feature wish-list
- removes any mention of gpt-j since support for it has been removed
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
* Adds support for GPT-NeoX, Gemma 2, OpenELM, ChatGLM, and Jais architectures (all with Kompute support)
* Also enables Kompute support for StarCoder2, XVERSE, Command R, and OLMo
* Includes a number of Kompute resource management fixes
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
