8000 llama : move vocab, grammar and sampling into separate files by ggerganov · Pull Request #8508 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

llama : move vocab, grammar and sampling into separate files #8508

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 11 commits into from
Jul 23, 2024
Merged

llama : move vocab, grammar and sampling into separate files #8508

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
0ddc8e3
llama : move sampling code into llama-sampling
ggerganov Jul 19, 2024
675f305
llama : move grammar code into llama-grammar
ggerganov Jul 16, 2024
5a71d1a
cont
ggerganov Jul 16, 2024
b4b242e
cont : pre-fetch rules
ggerganov Jul 16, 2024
689d377
cont
ggerganov Jul 19, 2024
e7dffa6
llama : deprecate llama_sample_grammar
ggerganov Jul 19, 2024
8000 8fef5b1
llama : move tokenizers into llama-vocab
ggerganov Jul 19, 2024
66ac80f
make : update llama.cpp deps [no ci]
ggerganov Jul 19, 2024
39fbaf9
llama : redirect external API to internal APIs
ggerganov Jul 19, 2024
dae3cae
llama : suffix the internal APIs with "_impl"
ggerganov Jul 22, 2024
fe28a7b
llama : clean-up
ggerganov Jul 23, 2024
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
Prev Previous commit
Next Next commit
llama : move tokenizers into llama-vocab 
ggml-ci
  • Loading branch information
@ggerganov
ggerganov committed Jul 22, 2024
commit 8fef5b1897188348f17ca7a88be0c2e4c327070e
4 changes: 2 additions & 2 deletions include/llama.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -906,10 +906,10 @@ extern "C" {
LLAMA_API llama_token llama_token_pad(const struct llama_model * model); // padding

// Returns -1 if unknown, 1 for true or 0 for false.
LLAMA_API int32_t llama_add_bos_token(const struct llama_model * model);
LLAMA_API int32_t llama_add_bos_token(const struct llama_model * model);

// Returns -1 if unknown, 1 for true or 0 for false.
LLAMA_API int32_t llama_add_eos_token(const struct llama_model * model);
LLAMA_API int32_t llama_add_eos_token(const struct llama_model * model);

// Codellama infill tokens
LLAMA_API llama_token llama_token_prefix(const struct llama_model * model); // Beginning of infill prefix
Expand Down
Loading
0