COMMITS
/ llama_cpp/llama_chat_format.py May 10, 2024
S
fix(security): Render all jinja templates in immutable sandbox (#1441)
Sigbjørn Skjæret committed
P
Merge pull request from GHSA-56xg-wfcc-g829
Patrick Peng committed
May 9, 2024
A
fix: free last image embed in llava chat handler
Andrei Betlen committed
May 8, 2024
A
fix: Make leading bos_token optional for image chat formats, fix nanollava system message
Andrei Betlen committed
S
fix: adding missing args in create_completion for functionary chat handler (#1430)
Sarunas Kalade committed
May 4, 2024
J
feat: Implement streaming for Functionary v2 + Bug fixes (#1419)
Jeffrey Fong committed
May 2, 2024
A
feat: Add llama-3-vision-alpha chat format
Andrei Betlen committed
April 30, 2024
A
A
fix: Ensure image renders before text in chat formats regardless of message content order.
Andrei Betlen committed
April 28, 2024
J
fix: Functionary bug fixes (#1385)
Jeffrey Fong committed
April 23, 2024
A
feat: Add Llama-3 chat format (#1371)
abk16 committed
April 20, 2024
April 18, 2024
L
feat: update grammar schema converter to match llama.cpp (#1353)
Lucca Zenóbio committed
April 17, 2024
A
Revert "feat: Update json to grammar (#1350)"
Andrei Betlen committed
L
feat: Update json to grammar (#1350)
Lucca Zenóbio committed
April 10, 2024
A
fix: pass correct type to chat handlers for chat completion logprobs
Andrei Betlen committed
April 5, 2024
March 31, 2024
W
feat: Add logprobs support to chat completions (#1311)
windspirit95 committed
March 23, 2024
A
fix: tool_call missing first token.
Andrei Betlen committed
March 19, 2024
March 18, 2024
J
fix: Fix and optimize functionary chat handler (#1282)
Jeffrey Fong committed
March 15, 2024
A
fix: json mode
Andrei Betlen committed
March 9, 2024
K
fix: Check for existence of clip model path (#1264)
Kevin Cao committed
February 26, 2024
A
fix: positional arguments only for low-level api
Andrei Betlen committed
A
fix: llava this function takes at least 4 arguments (0 given)
Andrei Betlen committed
February 23, 2024
L
feat: Auto detect Mixtral's slightly different format (#1214)
Luke Stanley committed
A
feat: Add Google's Gemma formatting via `chat_format="gemma"` (#1210)
Alvaro Bartolome committed
February 14, 2024
A
fix: Update openbuddy prompt format. Closes #1155
Andrei Betlen committed
A
fix: more chatml-function-calling fixes
Andrei Betlen committed
February 13, 2024
A
fix: missing generation_prompt in chatml-function-calling
Andrei Betlen committed
A
fix: minor formatting bugs for chatml-function-calling
Andrei Betlen committed
February 12, 2024
A
feat: Generic chatml Function Calling (#957)
Andrei committed
February 8, 2024
January 31, 2024
A
fix: Pass raise_exception and add_generation_prompt to jinja2 chat template
Andrei Betlen committed
January 29, 2024
A
Automatically set chat format from gguf (#1110)
Andrei committed
A
Add chat format test.
Andrei Betlen committed
R
Add mistral instruct chat format as "mistral-instruct" (#799)
Rafaelblsilva committed
January 27, 2024
A
Add json schema mode (#1122)
Andrei committed
January 22, 2024
A
fix: use both eos and bos tokens as stop sequences for hf-tokenizer-config chat format.
Andrei Betlen committed
January 21, 2024
A
feat: Add add_generation_prompt option for jinja2chatformatter.
Andrei Betlen committed
January 19, 2024
A
feat: Add Jinja2ChatFormatter
Andrei Betlen committed
A
January 4, 2024
F
Add Saiga chat format. (#1050)
Fedor Moiseev committed
X
Added ChatGLM chat format (#1059)
xaviviro committed
December 14, 2023
Y
Add qwen chat format (#1005)
yhfgyyf committed
December 12, 2023
C
Add Pygmalion chat format (#986)
chiensen committed
November 26, 2023
G
fix: Typo in the Open Orca chat format #874 (#947)
Gardner Bickford committed
November 24, 2023
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed