 Olivier Chafik
|
5cf5e7d490
`build`: generate hex dump of server assets during build (#6661)
|
1 жил өмнө |
 Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
1 жил өмнө |
|
Georgi Gerganov
|
b9cc76d87e
ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
|
1 жил өмнө |
 Wouter
|
7dbdba5690
llama : add llama-3 chat template (#6751)
|
1 жил өмнө |
 pmysl
|
c1386c936e
gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
|
1 жил өмнө |
 Jan Boon
|
e8d35f47cb
doc : add link to falcon (#6789)
|
1 жил өмнө |
 Mohammadreza Hendiani
|
2cca09d509
readme : add Fedora instructions (#6783)
|
1 жил өмнө |
 Justine Tunney
|
89b0bf0d5d
llava : use logger in llava-cli (#6797)
|
1 жил өмнө |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 жил өмнө |
|
Jan Boon
|
b8109bc013
doc : server tests require llama to be built with curl enabled (#6788)
|
1 жил өмнө |
|
Georgi Gerganov
|
aed82f6837
common : try to fix Android CI (#6780)
|
1 жил өмнө |
 loonerin
|
0e4802b2ec
ci: add ubuntu latest release and fix missing build number (mac & ubuntu) (#6748)
|
1 жил өмнө |
 Pierrick Hymbert
|
637e9a86c2
server: static: upstream upgrade (#6765)
|
1 жил өмнө |
 nopperl
|
9958c81b79
Implement the OLMo architecture (#6741)
|
1 жил өмнө |
 Austin
|
8b1b1f4982
train : add general name (#6752)
|
1 жил өмнө |
 Neo Zhang
|
bca40e9814
fix wrong parameter in cmd in readme-sycl.md (#6755)
|
1 жил өмнө |
 slaren
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
1 жил өмнө |
 Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
1 жил өмнө |
 Ren Xuancheng
|
e11b2e6e1e
Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)
|
1 жил өмнө |
|
slaren
|
c71bfd736e
llama : fix compatibility with old 2 expert models (#6735)
|
1 жил өмнө |
|
Georgi Gerganov
|
3b8f1ec4b1
llamafile : tmp disable + build sgemm.o when needed (#6716)
|
1 жил өмнө |
 Yaroslav
|
8dd1ec8b3f
readme : add UI (#6724)
|
1 жил өмнө |
 Zheng.Deng
|
facb8b56f8
convert : fix autoawq gemma (#6704)
|
1 жил өмнө |
|
Georgi Gerganov
|
532c1737a1
llama : make general.name optional (#6709)
|
1 жил өмнө |
|
Georgi Gerganov
|
666867b799
ggml : fix llamafile sgemm wdata offsets (#6710)
|
1 жил өмнө |
|
Justine Tunney
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
1 жил өмнө |
 Ashish
|
dbceec87c0
llama : add StableLM2 12B (#6635)
|
1 жил өмнө |
 Shijie
|
f4dea7da18
llama : add qwen2moe (#6074)
|
1 жил өмнө |
 Daniel Bevenius
|
8a56075b07
gritlm : add --outdir option to hf.sh script (#6699)
|
1 жил өмнө |
|
Georgi Gerganov
|
58227ffdeb
perplexity : require positive --ctx-size arg (#6695)
|
1 жил өмнө |
