 Gabe Goodhart
|
d590cd4c24
model : Granite MoE shared (#13269)
|
9 kuukautta sitten |
 City
|
3eac209319
mtmd : support InternVL 3 38B and 78B mmproj (#13443)
|
9 kuukautta sitten |
 Xuan-Son Nguyen
|
053367d149
mtmd : support InternVL 2.5 and 3 (#13422)
|
9 kuukautta sitten |
 Jared Van Bortel
|
2f567611c0
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
|
9 kuukautta sitten |
|
Xuan-Son Nguyen
|
074e42ab31
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
|
9 kuukautta sitten |
|
Xuan-Son Nguyen
|
8936784f7a
mtmd : add **vision** support for Mistral Small 3.1 (#13231)
|
9 kuukautta sitten |
 AT
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
9 kuukautta sitten |
|
Xuan-Son Nguyen
|
ecda2ec4b3
mtmd : Support Pixtral 12B (#13065)
|
9 kuukautta sitten |
|
Xuan-Son Nguyen
|
dc39a5e7a8
mtmd : support SmolVLM (version 1 and 2) (#13050)
|
9 kuukautta sitten |
|
Xuan-Son Nguyen
|
2016f07bd1
convert : experimental support for `--mmproj` flag (#13023)
|
9 kuukautta sitten |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 kuukautta sitten |
 Yuxuan Zhang
|
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)
|
10 kuukautta sitten |
 Bo Zheng
|
d3bd7193ba
llama : Support Qwen3 and Qwen3MoE (#12828)
|
10 kuukautta sitten |
|
Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
10 kuukautta sitten |
 Sigbjørn Skjæret
|
2c3f8b850a
llama : support BailingMoE (Ling) (#12634)
|
10 kuukautta sitten |
 Si1w
|
f125b8dccf
llama : add PLM GGUF Conversion & Inference Support (#12457)
|
10 kuukautta sitten |
|
Xuan-Son Nguyen
|
fbdfefe74e
llama : gemma3 : use output tensor if it exists in model weight (#12506)
|
10 kuukautta sitten |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 kuukautta sitten |
|
Xuan-Son Nguyen
|
7841fc723e
llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
|
11 kuukautta sitten |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
1 vuosi sitten |
 Georgi Gerganov
|
08f10f69c3
llama : remove notion of CLS token (#11064)
|
1 vuosi sitten |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 vuosi sitten |
 Pierrick Hymbert
|
f8feb4b01a
model: Add support for PhiMoE arch (#11003)
|
1 vuosi sitten |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
1 vuosi sitten |
 DAN™
|
46be942214
llama : add support for the cohere2 model architecture (#10900)
|
1 vuosi sitten |
 ymcki
|
6f0c9e034b
llama : support for Llama-3_1-Nemotron-51B (#10669)
|
1 vuosi sitten |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 vuosi sitten |
 Valentin Mamedov
|
a0974156f3
llama : add Deepseek MoE v1 & GigaChat models (#10827)
|
1 vuosi sitten |
 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 vuosi sitten |
 Robert Collins
|
62e84d9848
llama : add 128k yarn context for Qwen (#10698)
|
1 vuosi sitten |
