 Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
il y a 1 an |
 Anas Ahouzi
|
69917dfa55
py : fix StableLM conversion after config.json changes (#5703)
|
il y a 1 an |
 Pierrick Hymbert
|
9e359a4f47
server: continue to update other slots on embedding concurrent request (#5699)
|
il y a 1 an |
 Kawrakow
|
4c4cb30736
IQ3_S: a much better alternative to Q3_K (#5676)
|
il y a 1 an |
|
Pierrick Hymbert
|
525213d2f5
server: init functional tests (#5566)
|
il y a 1 an |
 AlpinDale
|
fd43d66f46
server : add KV cache quantization options (#5684)
|
il y a 1 an |
 Jared Van Bortel
|
54fbcd2ce6
convert : fix missing ftype for gemma (#5690)
|
il y a 1 an |
|
Jared Van Bortel
|
15499eb942
mpt : do not duplicate token_embd.weight on disk (#5670)
|
il y a 1 an |
|
Georgi Gerganov
|
96633eeca1
gemma : use more bits for the token_embd.weight tensor (#5650)
|
il y a 1 an |
|
Georgi Gerganov
|
847eedbdb2
py : add Gemma conversion from HF models (#5647)
|
il y a 1 an |
|
Georgi Gerganov
|
7e4f339c40
ggml : always define ggml_fp16_t as uint16_t (#5666)
|
il y a 1 an |
|
Georgi Gerganov
|
334f76fa38
sync : ggml
|
il y a 1 an |
|
Georgi Gerganov
|
efd56b1c21
ggml : 32-bit arm compat (whisper/1891)
|
il y a 1 an |
 Someone
|
201294ae17
nix: init singularity and docker images (#5056)
|
il y a 1 an |
|
Georgi Gerganov
|
5a9e2f60ba
py : minor fixes (#5668)
|
il y a 1 an |
 Xuan Son Nguyen
|
373ee3fbba
Add Gemma chat template (#5665)
|
il y a 1 an |
|
Someone
|
4cb4d8b22d
workflows: nix: hardcode cachix ids, build unconditionally (#5663)
|
il y a 1 an |
|
Georgi Gerganov
|
3a03541ced
minor : fix trailing whitespace (#5638)
|
il y a 1 an |
|
Georgi Gerganov
|
56d03d92be
readme : update hot topics
|
il y a 1 an |
|
Xuan Son Nguyen
|
a46f50747b
server : fallback to chatml, add AlphaMonarch chat template (#5628)
|
il y a 1 an |
 Alexey Parfenov
|
c5688c6250
server : clarify some params in the docs (#5640)
|
il y a 1 an |
 Dat Quoc Nguyen
|
4ef245a92a
mpt : add optional bias tensors (#5638)
|
il y a 1 an |
 slaren
|
973053d8b0
llama : fix loading models with shared tok_embd and output (#5651)
|
il y a 1 an |
|
Xuan Son Nguyen
|
7c8bcc11dc
Add docs for llama_chat_apply_template (#5645)
|
il y a 1 an |
|
slaren
|
7fe4678b02
llama : fix session save/load with quantized KV (#5649)
|
il y a 1 an |
|
slaren
|
ba2135ccae
gemma : allow offloading the output tensor (#5646)
|
il y a 1 an |
|
Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
il y a 1 an |
|
Georgi Gerganov
|
5022cf242d
sync : ggml
|
il y a 1 an |
|
Pierrick Hymbert
|
1ecea255eb
server: health: fix race condition on slots data using tasks queue (#5634)
|
il y a 1 an |
 Ettore Di Giacinto
|
a00a35cef9
readme : add LocalAI to the availables UI (#5629)
|
il y a 1 an |
