 Xuan-Son Nguyen
|
e047f9ee9d
mtmd: fix use_non_causal being reported incorrectly (#18793)
|
2 weeks ago |
 Simranjeet Singh
|
a61c8bc3bf
mtmd: Add Gemma3n multimodal support with MobileNetV5 vision encoder (#18256)
|
2 weeks ago |
 Tarek Dakhran
|
4974bf53cf
model : mtmd : make input norm optional in LFM2-VL (#18594)
|
3 weeks ago |
 tt
|
ced765be44
model: support youtu-vl model (#18479)
|
4 weeks ago |
 Henry147147
|
9b8329de7a
mtmd : Adding support for Nvidia Music Flamingo Model (#18470)
|
4 weeks ago |
|
Xuan-Son Nguyen
|
8ea958d4d9
model : add ASR support for LFM2-Audio-1.5B (conformer) (#18106)
|
1 month ago |
|
Xuan-Son Nguyen
|
3d86c6c2b5
model: support GLM4V vision encoder (#18042)
|
1 month ago |
|
Xuan-Son Nguyen
|
96a181a933
mtmd: refactor audio preprocessing (#17978)
|
1 month ago |
 piDack
|
745fa0e78b
model : add glm-asr support (#17901)
|
1 month ago |
 Haowei Wu
|
37f5a1093b
mtmd: enhance image resizing in llava_uhd (#18014)
|
1 month ago |
|
Xuan-Son Nguyen
|
e39a2ce66d
clip: move model cgraphs into their own files (#17965)
|
1 month ago |
|
Xuan-Son Nguyen
|
c6b2c9310c
mtmd: some small clean up (#17909)
|
1 month ago |
 Georgi Gerganov
|
4dff236a52
ggml : remove GGML_KQ_MASK_PAD constant (#17910)
|
1 month ago |
|
Xuan-Son Nguyen
|
a96283adc4
mtmd: fix --no-warmup (#17695)
|
1 month ago |
|
Xuan-Son Nguyen
|
ecf74a8417
mtmd: add mtmd_context_params::warmup option (#17652)
|
1 month ago |
|
Tarek Dakhran
|
2ba719519d
model: LFM2-VL fixes (#17577)
|
2 months ago |
|
Xuan-Son Nguyen
|
7f8ef50cce
clip: fix nb calculation for qwen3-vl (#17594)
|
2 months ago |
 Han Qingzhe
|
1d594c295c
clip: (minicpmv) fix resampler kq_scale (#17516)
|
2 months ago |
|
Xuan-Son Nguyen
|
9b17d74ab7
mtmd: add mtmd_log_set (#17268)
|
2 months ago |
|
Xuan-Son Nguyen
|
4b13a684c5
mtmd: fix patch_size initialized to random value in audio models (#17128)
|
2 months ago |
|
Xuan-Son Nguyen
|
4882f0ff78
clip: implement minicpm-v sinusoidal embd using GGML (#17036)
|
2 months ago |
|
Xuan-Son Nguyen
|
92bb84f775
mtmd: allow QwenVL to process larger image by default (#17020)
|
2 months ago |
|
Xuan-Son Nguyen
|
2f0c2db43e
mtmd: improve struct initialization (#16981)
|
2 months ago |
|
Xuan-Son Nguyen
|
070ff4d535
mtmd: add --image-min/max-tokens (#16921)
|
2 months ago |
|
Xuan-Son Nguyen
|
bf7b0c9725
mtmd: pad mask for qwen2.5vl (#16954)
|
2 months ago |
 Zhiyong Wang
|
6b9a52422b
model: add Janus Pro for image understanding (#16906)
|
2 months ago |
|
Georgi Gerganov
|
2f966b8ed8
clip : use FA (#16837)
|
2 months ago |
|
Xuan-Son Nguyen
|
cf659bbb8e
mtmd: refactor preprocessing + support max/min pixels (#16878)
|
2 months ago |
 JJJYmmm
|
d261223d24
model: add support for qwen3vl series (#16780)
|
3 months ago |
 Tianyue-Zhao
|
bacddc049a
model: Add support for CogVLM model (#15002)
|
3 months ago |
