 Junyang Lin
|
3fec68be4e
convert : add support of codeqwen due to tokenizer (#6707)
|
преди 1 година |
 liuwei-git
|
c8297c6af5
llama : add phi3 support (#6852)
|
преди 1 година |
 Anas Ahouzi
|
4e96a812b3
[SYCL] Windows default build instructions without -DLLAMA_SYCL_F16 flag activated (#6767)
|
преди 1 година |
 Justine Tunney
|
192090bae4
llamafile : improve sgemm.cpp (#6796)
|
преди 1 година |
 Dave Airlie
|
e931888d50
ggml : fix calloc argument ordering. (#6820)
|
преди 1 година |
 Georgi Gerganov
|
8960fe86ae
llama : fix typo in <|im_end|> token text (#6745)
|
преди 1 година |
 Pierrick Hymbert
|
c0956b09ba
ci: fix job are cancelling each other (#6781)
|
преди 1 година |
 github-actions[bot]
|
e9b4a1bf68
flake.lock: Update
|
преди 1 година |
 Olivier Chafik
|
5cf5e7d490
`build`: generate hex dump of server assets during build (#6661)
|
преди 1 година |
|
Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
преди 1 година |
|
Georgi Gerganov
|
b9cc76d87e
ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
|
преди 1 година |
 Wouter
|
7dbdba5690
llama : add llama-3 chat template (#6751)
|
преди 1 година |
 pmysl
|
c1386c936e
gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
|
преди 1 година |
 Jan Boon
|
e8d35f47cb
doc : add link to falcon (#6789)
|
преди 1 година |
 Mohammadreza Hendiani
|
2cca09d509
readme : add Fedora instructions (#6783)
|
преди 1 година |
|
Justine Tunney
|
89b0bf0d5d
llava : use logger in llava-cli (#6797)
|
преди 1 година |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
преди 1 година |
|
Jan Boon
|
b8109bc013
doc : server tests require llama to be built with curl enabled (#6788)
|
преди 1 година |
|
Georgi Gerganov
|
aed82f6837
common : try to fix Android CI (#6780)
|
преди 1 година |
 loonerin
|
0e4802b2ec
ci: add ubuntu latest release and fix missing build number (mac & ubuntu) (#6748)
|
преди 1 година |
|
Pierrick Hymbert
|
637e9a86c2
server: static: upstream upgrade (#6765)
|
преди 1 година |
 nopperl
|
9958c81b79
Implement the OLMo architecture (#6741)
|
преди 1 година |
 Austin
|
8b1b1f4982
train : add general name (#6752)
|
преди 1 година |
 Neo Zhang
|
bca40e9814
fix wrong parameter in cmd in readme-sycl.md (#6755)
|
преди 1 година |
 slaren
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
преди 1 година |
 Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
преди 1 година |
 Ren Xuancheng
|
e11b2e6e1e
Qwen2 : assume tied weights if lm_head/output weights is missing (#6738)
|
преди 1 година |
|
slaren
|
c71bfd736e
llama : fix compatibility with old 2 expert models (#6735)
|
преди 1 година |
|
Georgi Gerganov
|
3b8f1ec4b1
llamafile : tmp disable + build sgemm.o when needed (#6716)
|
преди 1 година |
 Yaroslav
|
8dd1ec8b3f
readme : add UI (#6724)
|
преди 1 година |
