 Xuan-Son Nguyen
|
2016f07bd1
convert : experimental support for `--mmproj` flag (#13023)
|
9 달 전 |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 달 전 |
 Yuxuan Zhang
|
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)
|
9 달 전 |
 Daniel Han
|
ec6c09d0fa
convert : Llama4 RoPE fix (#12889)
|
9 달 전 |
|
Xuan-Son Nguyen
|
5b1f13cb64
convert : proper tensor name mapping for llama4 (#12870)
|
9 달 전 |
|
Xuan-Son Nguyen
|
64eda5deb9
convert : ability to lazy-load safetensors remotely without downloading to disk (#12820)
|
10 달 전 |
 Bo Zheng
|
d3bd7193ba
llama : Support Qwen3 and Qwen3MoE (#12828)
|
10 달 전 |
|
Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
10 달 전 |
 Sigbjørn Skjæret
|
5936a616e4
convert : BailingMoE : fix qkv split when head_dim is 0 (#12687)
|
10 달 전 |
|
Sigbjørn Skjæret
|
35782aeedb
convert : BailingMoE : avoid setting rope_dim to 0 (#12678)
|
10 달 전 |
|
Sigbjørn Skjæret
|
403fbacbbc
convert : Qwerky : use lora_rank_tokenshift and lora_rank_decay if present (#12667)
|
10 달 전 |
|
Sigbjørn Skjæret
|
2c3f8b850a
llama : support BailingMoE (Ling) (#12634)
|
10 달 전 |
 Juyoung Suk
|
b3de7cac73
llama : add Trillion 7B model support (#12556)
|
10 달 전 |
 Si1w
|
f125b8dccf
llama : add PLM GGUF Conversion & Inference Support (#12457)
|
10 달 전 |
 Csaba Kecskemeti
|
d5c6309d91
convert : Support Qwen2_5_VLForConditionalGeneration (#12595)
|
10 달 전 |
 Georgi Gerganov
|
df4d20cd53
convert : fix squeeze for ssm_conv tensors (#12573)
|
10 달 전 |
|
Sigbjørn Skjæret
|
53af4dba42
convert: fix Mistral3/Gemma3 model hparams init (#12571)
|
10 달 전 |
 compilade
|
00d53800e0
llama-vocab : add SuperBPE pre-tokenizer (#12532)
|
10 달 전 |
 Bartowski
|
732b5fbf5e
convert : avoid calls to tokenizer.added_tokens_decoder (#12473)
|
10 달 전 |
|
Sigbjørn Skjæret
|
108e53c2f1
llama : add support for GPT2, Bloom and CodeShell tied word embeddings (#12456)
|
10 달 전 |
|
Xuan-Son Nguyen
|
29fff308c7
llama : support converting Mistral Small text-only (#12450)
|
10 달 전 |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 달 전 |
|
Xuan-Son Nguyen
|
7841fc723e
llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
|
10 달 전 |
 Xuan-Son Nguyen
|
c43a3e7996
llama : add Phi-4-mini support (supersede #12099) (#12108)
|
11 달 전 |
|
Georgi Gerganov
|
68ff663a04
repo : update links to new url (#11886)
|
11 달 전 |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
1 년 전 |
|
Xuan Son Nguyen
|
ec7f3ac9ab
llama : add support for Deepseek-R1-Qwen distill model (#11310)
|
1 년 전 |
 RunningLeon
|
4dbc8b9cb7
llama : add internlm3 support (#11233)
|
1 년 전 |
 Daniel Bevenius
|
2739a71e4b
convert : sort print supported models [no ci] (#11179)
|
1 년 전 |
|
Daniel Bevenius
|
ff3fcabc72
convert : add --print-supported-models option (#11172)
|
1 년 전 |
