 Jared Van Bortel
|
54fbcd2ce6
convert : fix missing ftype for gemma (#5690)
|
1 år sedan |
|
Jared Van Bortel
|
15499eb942
mpt : do not duplicate token_embd.weight on disk (#5670)
|
1 år sedan |
 Georgi Gerganov
|
96633eeca1
gemma : use more bits for the token_embd.weight tensor (#5650)
|
1 år sedan |
|
Georgi Gerganov
|
847eedbdb2
py : add Gemma conversion from HF models (#5647)
|
1 år sedan |
|
Georgi Gerganov
|
7e4f339c40
ggml : always define ggml_fp16_t as uint16_t (#5666)
|
1 år sedan |
|
Georgi Gerganov
|
334f76fa38
sync : ggml
|
1 år sedan |
|
Georgi Gerganov
|
efd56b1c21
ggml : 32-bit arm compat (whisper/1891)
|
1 år sedan |
 Someone
|
201294ae17
nix: init singularity and docker images (#5056)
|
1 år sedan |
|
Georgi Gerganov
|
5a9e2f60ba
py : minor fixes (#5668)
|
1 år sedan |
 Xuan Son Nguyen
|
373ee3fbba
Add Gemma chat template (#5665)
|
1 år sedan |
|
Someone
|
4cb4d8b22d
workflows: nix: hardcode cachix ids, build unconditionally (#5663)
|
1 år sedan |
|
Georgi Gerganov
|
3a03541ced
minor : fix trailing whitespace (#5638)
|
1 år sedan |
|
Georgi Gerganov
|
56d03d92be
readme : update hot topics
|
1 år sedan |
|
Xuan Son Nguyen
|
a46f50747b
server : fallback to chatml, add AlphaMonarch chat template (#5628)
|
1 år sedan |
 Alexey Parfenov
|
c5688c6250
server : clarify some params in the docs (#5640)
|
1 år sedan |
 Dat Quoc Nguyen
|
4ef245a92a
mpt : add optional bias tensors (#5638)
|
1 år sedan |
 slaren
|
973053d8b0
llama : fix loading models with shared tok_embd and output (#5651)
|
1 år sedan |
|
Xuan Son Nguyen
|
7c8bcc11dc
Add docs for llama_chat_apply_template (#5645)
|
1 år sedan |
|
slaren
|
7fe4678b02
llama : fix session save/load with quantized KV (#5649)
|
1 år sedan |
|
slaren
|
ba2135ccae
gemma : allow offloading the output tensor (#5646)
|
1 år sedan |
|
Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
1 år sedan |
|
Georgi Gerganov
|
5022cf242d
sync : ggml
|
1 år sedan |
 Pierrick Hymbert
|
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
|
1 år sedan |
 Ettore Di Giacinto
|
a00a35cef9
readme : add LocalAI to the availables UI (#5629)
|
1 år sedan |
|
Georgi Gerganov
|
eccd7a26dd
sync : ggml (#5633)
|
1 år sedan |
|
Georgi Gerganov
|
c14f72db9c
readme : update hot topics
|
1 år sedan |
 Daniel Bevenius
|
cc6cac08e3
llava : add --skip-unknown to 1.6 convert.py (#5632)
|
1 år sedan |
 postmasters
|
580111d42b
llama : add `gemma` model (#5631)
|
1 år sedan |
 Meng, Hengyu
|
88c46cbdac
[SYCL] conext add name (#5624)
|
1 år sedan |
 Kawrakow
|
a14679cc30
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)
|
1 år sedan |
