MORPH
SIGN IN SIGN UP
abetlen / llama-cpp-python UNCLAIMED

Python bindings for llama.cpp

0 0 1 Python

COMMITS

/ llama_cpp/llama_chat_format.py
82ad829c4c95af4435c30cd07dfa51025e404712
July 3, 2025
A
fix: Use num_threads from llama model for mtmd
Andrei Betlen committed
07a979f
A
feat: Add support for new mtmd api, add Qwen2.5-VL chat handler
Andrei Betlen committed
cd548bd
December 6, 2024
A
fix: chat API logprobs format (#1788)
Adam Jones committed
4f0ec65
August 30, 2024
A
fix: Use system message in og qwen format. Closes #1697
Andrei Betlen committed
98eb092
August 29, 2024
A
fix: Update name to MiniCPMv26ChatHandler
Andrei Betlen committed
e251a0b
A
feat: Add MiniCPMv26 chat handler.
Andrei Betlen committed
f70df82
July 9, 2024
A
fix(minor): Minor ruff fixes
Andrei Betlen committed
08f2bb3
A
fix(misc): Format
Andrei Betlen committed
c1ae815
June 4, 2024
S
fix: Avoid duplicate special tokens in chat formats (#1439)
Sigbjørn Skjæret committed
027f7bc
June 3, 2024
A
misc: Improve llava error messages
Andrei Betlen committed
6b018e0
May 29, 2024
A
fix: Fix typo in Llama3VisionAlphaChatHandler. Closes #1488
Andrei Betlen committed
165b4dc
May 10, 2024
A
fix: Clear kv cache to avoid kv bug when image is evaluated first
Andrei Betlen committed
ac55d0a
S
fix(security): Render all jinja templates in immutable sandbox (#1441)
Sigbjørn Skjæret committed
561e880
P
Merge pull request from GHSA-56xg-wfcc-g829
Patrick Peng committed
b454f40
May 9, 2024
A
fix: free last image embed in llava chat handler
Andrei Betlen committed
3757328
May 8, 2024
A
fix: Make leading bos_token optional for image chat formats, fix nanollava system message
Andrei Betlen committed
7712263
S
fix: adding missing args in create_completion for functionary chat handler (#1430)
Sarunas Kalade committed
903b28a
May 4, 2024
J
feat: Implement streaming for Functionary v2 + Bug fixes (#1419)
Jeffrey Fong committed
1f56c64
May 2, 2024
A
feat: Add llama-3-vision-alpha chat format
Andrei Betlen committed
31b1d95
April 30, 2024
A
fix: Change default verbose value of verbose in image chat format handlers to True to match Llama
Andrei Betlen committed
4f01c45
A
fix: Ensure image renders before text in chat formats regardless of message content order.
Andrei Betlen committed
3489ef0
A
feat: Generic Chat Formats, Tool Calling, and Huggingface Pull Support for Multimodal Models (Obsidian, LLaVA1.6, Moondream) (#1147)
Andrei committed
fe2da09
April 28, 2024
J
fix: Functionary bug fixes (#1385)
Jeffrey Fong committed
f178636
April 23, 2024
A
feat: Add Llama-3 chat format (#1371)
abk16 committed
8559e8c
April 20, 2024
A
feat: Add stopping_criteria to ChatFormatter, allow stopping on arbitrary token ids, fixes llama3 instruct
Andrei Betlen committed
cc81afe
April 18, 2024
L
feat: update grammar schema converter to match llama.cpp (#1353)
Lucca Zenóbio committed
4f42664
April 17, 2024
A
Revert "feat: Update json to grammar (#1350)"
Andrei Betlen committed
fa4bb0c
L
feat: Update json to grammar (#1350)
Lucca Zenóbio committed
610a592
April 10, 2024
A
fix: pass correct type to chat handlers for chat completion logprobs
Andrei Betlen committed
bb65b4d
April 5, 2024
A
fix: missing logprobs in response, incorrect response type for functionary, minor type issues. Closes #1328 Closes #1314
Andrei Betlen committed
1ae3abb
March 31, 2024
W
feat: Add logprobs support to chat completions (#1311)
windspirit95 committed
aa9f1ae
March 23, 2024
A
fix: tool_call missing first token.
Andrei Betlen committed
c1325dc
March 19, 2024
A
feat: Add tools/functions variables to Jinja2ChatFormatter, add function response formatting for all simple chat formats (#1273)
Andrei committed
60d8498
March 18, 2024
J
fix: Fix and optimize functionary chat handler (#1282)
Jeffrey Fong committed
8a60c7b
March 15, 2024
A
fix: json mode
Andrei Betlen committed
20e6815
March 9, 2024
K
fix: Check for existence of clip model path (#1264)
Kevin Cao committed
1f3156d
February 26, 2024
A
fix: positional arguments only for low-level api
Andrei Betlen committed
dbaba30
A
fix: typo
Andrei Betlen committed
78e536d
A
fix: llava this function takes at least 4 arguments (0 given)
Andrei Betlen committed
8383a9e
February 23, 2024
L
feat: Auto detect Mixtral's slightly different format (#1214)
Luke Stanley committed
8584962
A
feat: Add Google's Gemma formatting via `chat_format="gemma"` (#1210)
Alvaro Bartolome committed
251a8a2
February 14, 2024
A
fix: Update openbuddy prompt format. Closes #1155
Andrei Betlen committed
07a7837
A
fix: more chatml-function-calling fixes
Andrei Betlen committed
345215a
February 13, 2024
A
fix: missing generation_prompt in chatml-function-calling
Andrei Betlen committed
68fb71b
A
fix: minor formatting bugs for chatml-function-calling
Andrei Betlen committed
4b0e332
February 12, 2024
A
feat: Generic chatml Function Calling (#957)
Andrei committed
153a004
February 8, 2024
J
feat: Integrate functionary v1.4 and v2 models + add custom tokenizer support to Llama class (#1078)
Jeffrey Fong committed
9018270
January 31, 2024
A
fix: Pass raise_exception and add_generation_prompt to jinja2 chat template
Andrei Betlen committed
078cca0
January 29, 2024
A
Automatically set chat format from gguf (#1110)
Andrei committed
da003d8
A
Add chat format test.
Andrei Betlen committed
9ae5819