 Jared Van Bortel
|
511f52c334
build : enable libstdc++ assertions for debug builds (#4275)
|
пре 2 година |
 CausalLM
|
03562f3a86
llama : support attention bias on LLaMA architecture (#4283)
|
пре 2 година |
 Shijie
|
37c746d687
llama : add Qwen support (#4281)
|
пре 2 година |
 Georgi Gerganov
|
880f57973b
llama : fix integer overflow during quantization (#4284)
|
пре 2 година |
 Daniel Bevenius
|
8d6d9f033b
py : add requirements file for convert-hf-to-gguf.py (#4277)
|
пре 2 година |
|
Georgi Gerganov
|
ef47ec18da
ggml : add ggml_soft_max_ext (#4256)
|
пре 2 година |
 Ziad Ben Hadj-Alouane
|
1d144112c0
server : add --log-disable to disable logging to file (#4260)
|
пре 2 година |
|
Ziad Ben Hadj-Alouane
|
f43f09366d
server : add single-client multi-prompt support (#4232)
|
пре 2 година |
 WillCorticesAI
|
d2809a3ba2
make : fix Apple clang determination bug (#4272)
|
пре 2 година |
|
Jared Van Bortel
|
15f5d96037
build : fix build info generation and cleanup Makefile (#3920)
|
пре 2 година |
 John
|
33c9892af5
llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
|
пре 2 година |
 Andrew Godfrey
|
8efa0f6ebe
main : pass LOG_TEE callback to llama.cpp log (#4033)
|
пре 2 година |
 vodkaslime
|
524907aa76
readme : fix (#4135)
|
пре 2 година |
 Juraj Bednar
|
3bd2c7ce1b
docker : add finetune option (#4211)
|
пре 2 година |
 Miwa / Ensan
|
bde629bb53
batched.swift : update README.md (#4214)
|
пре 2 година |
 Li Tan
|
f7f9e06212
cmake : fix the metal file foder path (#4217)
|
пре 2 година |
 Dawid Wysocki
|
74daabae69
readme : fix typo (#4253)
|
пре 2 година |
|
Daniel Bevenius
|
b18c66ca6e
llama : fix alignment of general.name in print meta (#4254)
|
пре 2 година |
 slaren
|
f4d973cecb
convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#4258)
|
пре 2 година |
 tarcey
|
954e22858c
llama : fix typical sampling (#4261)
|
пре 2 година |
 rhjdvsgsgks
|
e2bd725f4b
py : fix oai proxy (#3972)
|
пре 2 година |
|
Georgi Gerganov
|
1f5cd83275
examples : add readme files
|
пре 2 година |
 Peter Sugihara
|
4fea3420ee
readme : add FreeChat (#4248)
|
пре 2 година |
|
Jared Van Bortel
|
64e64aa255
ggml : restore abort() in GGML_ASSERT (#4242)
|
пре 2 година |
|
Georgi Gerganov
|
8406b0924b
ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240)
|
пре 2 година |
 bandoti
|
b38a16dfcf
cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970)
|
пре 2 година |
 Kasumi
|
0dab8cd7cc
readme : add Amica to UI list (#4230)
|
пре 2 година |
 Bailey Chittle
|
bb03290c17
examples : iOS example with swift ui (#4159)
|
пре 2 година |
|
Jared Van Bortel
|
f3b269813f
ggml : fix -Warray-bounds warning with gcc (#4231)
|
пре 2 година |
|
Georgi Gerganov
|
3e73d31d9c
lookahead : support `-n -1` infinite generation
|
пре 2 година |
