 Xuan-Son Nguyen
|
074e42ab31
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
|
9 hónapja |
|
Xuan-Son Nguyen
|
8936784f7a
mtmd : add **vision** support for Mistral Small 3.1 (#13231)
|
9 hónapja |
 AT
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
9 hónapja |
|
Xuan-Son Nguyen
|
ecda2ec4b3
mtmd : Support Pixtral 12B (#13065)
|
9 hónapja |
|
Xuan-Son Nguyen
|
dc39a5e7a8
mtmd : support SmolVLM (version 1 and 2) (#13050)
|
9 hónapja |
|
Xuan-Son Nguyen
|
2016f07bd1
convert : experimental support for `--mmproj` flag (#13023)
|
9 hónapja |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 hónapja |
 Yuxuan Zhang
|
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)
|
9 hónapja |
|
Xuan-Son Nguyen
|
5b1f13cb64
convert : proper tensor name mapping for llama4 (#12870)
|
9 hónapja |
 Sigbjørn Skjæret
|
2c3f8b850a
llama : support BailingMoE (Ling) (#12634)
|
10 hónapja |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 hónapja |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 éve |
 Pierrick Hymbert
|
f8feb4b01a
model: Add support for PhiMoE arch (#11003)
|
1 éve |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
1 éve |
 ymcki
|
6f0c9e034b
llama : support for Llama-3_1-Nemotron-51B (#10669)
|
1 éve |
 Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 éve |
 Valentin Mamedov
|
a0974156f3
llama : add Deepseek MoE v1 & GigaChat models (#10827)
|
1 éve |
|
Georgi Gerganov
|
c5ede3849f
convert : add custom attention mapping
|
1 éve |
 Shane A
|
80acb7b430
Rename Olmo1124 to Olmo2 (#10500)
|
1 éve |
|
Shane A
|
a88ad007de
llama : add OLMo November 2024 support (#10394)
|
1 éve |
 compilade
|
1927378bcc
convert : refactor rope_freqs generation (#9396)
|
1 éve |
|
Georgi Gerganov
|
f4d2b8846a
llama : add reranking support (#9510)
|
1 éve |
 nopperl
|
9a913110cf
llama : add support for Chameleon (#8543)
|
1 éve |
 Gabe Goodhart
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
1 éve |
|
Shane A
|
0aadac10c7
llama : support OLMoE (#9462)
|
1 éve |
|
Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 éve |
 Minsoo Cheong
|
c679e0cb5c
llama : add EXAONE model support (#9025)
|
1 éve |
 Yoshi Suhara
|
2a24c8caa6
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
|
1 éve |
|
compilade
|
7acfd4e8d5
convert_hf : faster lazy safetensors (#8482)
|
1 éve |
 toyer
|
905942abdb
llama : support glm3 and glm4 (#8031)
|
1 éve |
