 Xuan-Son Nguyen
|
4882f0ff78
clip: implement minicpm-v sinusoidal embd using GGML (#17036)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
92bb84f775
mtmd: allow QwenVL to process larger image by default (#17020)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
2f0c2db43e
mtmd: improve struct initialization (#16981)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
070ff4d535
mtmd: add --image-min/max-tokens (#16921)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
bf7b0c9725
mtmd: pad mask for qwen2.5vl (#16954)
|
há 2 meses atrás |
 Zhiyong Wang
|
6b9a52422b
model: add Janus Pro for image understanding (#16906)
|
há 2 meses atrás |
 Georgi Gerganov
|
2f966b8ed8
clip : use FA (#16837)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
cf659bbb8e
mtmd: refactor preprocessing + support max/min pixels (#16878)
|
há 2 meses atrás |
 JJJYmmm
|
d261223d24
model: add support for qwen3vl series (#16780)
|
há 2 meses atrás |
 Tianyue-Zhao
|
bacddc049a
model: Add support for CogVLM model (#15002)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
e1ab084803
mtmd : fix idefics3 preprocessing (#16806)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
c55d53acec
model : add LightOnOCR-1B model (#16764)
|
há 2 meses atrás |
|
Xuan-Son Nguyen
|
1bb4f43380
mtmd : support home-cooked Mistral Small Omni (#14928)
|
há 3 meses atrás |
 Gabe Goodhart
|
ca71fb9b36
model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)
|
há 3 meses atrás |
 Aleksei Nikiforov
|
cc1cfa277b
mtmd : fix uninitialized variable in bicubic_resize (#16275)
|
há 3 meses atrás |
 Diego Devesa
|
50f4281a6f
llama : allow using iGPUs with --device (#15951)
|
há 4 meses atrás |
|
Xuan-Son Nguyen
|
79a546220c
mtmd : support Kimi VL model (#15458)
|
há 4 meses atrás |
 tc-mb
|
c4e9239064
model : support MiniCPM-V 4.5 (#15575)
|
há 4 meses atrás |
 Tarek Dakhran
|
e288693669
readme : model : mtdm : lfm2 improvements (#15476)
|
há 5 meses atrás |
 Michael Giba
|
b108e42904
ci : fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue (#15221)
|
há 5 meses atrás |
|
Xuan-Son Nguyen
|
f08c4c0d8d
mtmd : clean up clip_n_output_tokens (#15391)
|
há 5 meses atrás |
 Sigbjørn Skjæret
|
baa9255a45
llama : merge conts and reshapes and remove unnecessary cont (#15380)
|
há 5 meses atrás |
 Tarek Dakhran
|
65349f26f2
model : support vision LiquidAI LFM2-VL family (#15347)
|
há 5 meses atrás |
 rainred
|
cf9e5648a7
mtmd : Fix MinicpmV model converter and clip to avoid using hardcode. (#14750)
|
há 5 meses atrás |
|
tc-mb
|
952a47f455
mtmd : support MiniCPM-V 4.0 (#14983)
|
há 5 meses atrás |
|
Xuan-Son Nguyen
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
há 5 meses atrás |
 kiwi
|
749e0d27f0
mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503)
|
há 5 meses atrás |
 stduhpf
|
c8ade30036
Mtmd: add a way to select device for vision encoder (#14236)
|
há 6 meses atrás |
|
Sigbjørn Skjæret
|
28657a8229
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)
|
há 6 meses atrás |
 yuiseki
|
5d5c066de8
mtmd : fix Pixtral OOM with large images by capping image_size to 1024 (#14326)
|
há 7 meses atrás |
