 Sigbjørn Skjæret
|
e83ba3e460
llama : add support for jina-reranker-v2 (#13900)
|
8 months ago |
|
Sigbjørn Skjæret
|
5ca82fc1d7
convert : workaround for AutoConfig dummy labels (#13881)
|
8 months ago |
|
Sigbjørn Skjæret
|
6385b843a8
llama : add RobertaForSequenceClassification reranker support (#13875)
|
8 months ago |
 Đinh Trọng Huy
|
e0e3aa231d
llama : add support for BertForSequenceClassification reranker (#13858)
|
8 months ago |
|
Đinh Trọng Huy
|
aa6dff05be
convert: small addition to support LlamaModel (#13838)
|
8 months ago |
 Xuan-Son Nguyen
|
a3938fb53d
convert : fix qwen omni conversion (#13859)
|
8 months ago |
|
Xuan-Son Nguyen
|
26b79b6cb3
convert : fix tensor naming conflict for llama 4 vision (#13836)
|
8 months ago |
|
Xuan-Son Nguyen
|
bc583e3c63
mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)
|
8 months ago |
|
Xuan-Son Nguyen
|
40aaa8a403
mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760)
|
8 months ago |
|
Xuan-Son Nguyen
|
797990c4bc
mtmd : add ultravox audio input (#13623)
|
8 months ago |
 antichristHater
|
c76532e7ba
convert : add qwen2vl support for unsloth merges (#13686)
|
8 months ago |
|
Xuan-Son Nguyen
|
92ecdcc06a
mtmd : add vision support for llama 4 (#13282)
|
8 months ago |
|
Xuan-Son Nguyen
|
c531edfa34
convert : fix conversion for llama 4 (#13567)
|
9 months ago |
 Gabe Goodhart
|
d590cd4c24
model : Granite MoE shared (#13269)
|
9 months ago |
|
Sigbjørn Skjæret
|
d2a4ef05c6
vocab : add ByteDance-Seed/Seed-Coder (#13423)
|
9 months ago |
|
Xuan-Son Nguyen
|
053367d149
mtmd : support InternVL 2.5 and 3 (#13422)
|
9 months ago |
|
Sigbjørn Skjæret
|
1a844be132
convert : support rope_scaling type and rope_type (#13349)
|
9 months ago |
|
Xuan-Son Nguyen
|
32916a4907
clip : refactor graph builder (#13321)
|
9 months ago |
|
Sigbjørn Skjæret
|
764b85627b
convert : qwen2/3moe : set yarn metadata if present (#13331)
|
9 months ago |
|
Xuan-Son Nguyen
|
5215b91e93
clip : fix confused naming ffn_up and ffn_down (#13290)
|
9 months ago |
|
Sigbjørn Skjæret
|
ae803bfc3d
convert : bailingmoe : set yarn metadata if present (#13312)
|
9 months ago |
 ymcki
|
3bf785f3ef
llama : Llama-3_1-Nemotron-Ultra-253B-v1 support (#12843)
|
9 months ago |
 Jared Van Bortel
|
2f567611c0
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
|
9 months ago |
|
Jared Van Bortel
|
7d2123484e
convert : use correct context length for nomic-embed-text-v2 (#13216)
|
9 months ago |
|
Xuan-Son Nguyen
|
074e42ab31
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
|
9 months ago |
|
Xuan-Son Nguyen
|
dcf886007d
convert : explicitly disable trust_remote_code for AutoConfig (#13246)
|
9 months ago |
|
Xuan-Son Nguyen
|
8936784f7a
mtmd : add **vision** support for Mistral Small 3.1 (#13231)
|
9 months ago |
|
Xuan-Son Nguyen
|
3e168bede4
convert : improve model arch handling (#13122)
|
9 months ago |
|
Xuan-Son Nguyen
|
07c2e2f76c
convert : correct typo image_mean --> image_std (#13208)
|
9 months ago |
 AT
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
9 months ago |
