 Sigbjørn Skjæret
|
5c8a717128
convert : refactor rope scaling handling (#18013)
|
1 月之前 |
 Georgi Gerganov
|
7bed317f53
models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)
|
1 月之前 |
 Xuan-Son Nguyen
|
9e79b0116e
convert: allow using quantized Mistral weight (#17889)
|
2 月之前 |
 philip-essential
|
1d2a1ab73d
model : support Rnj-1 (#17811)
|
2 月之前 |
|
Xuan-Son Nguyen
|
dbc15a7967
convert: support Mistral 3 Large MoE (#17730)
|
2 月之前 |
 SmartestWashingMachine
|
3659aa28e9
convert: use existing local chat_template if mistral-format model has one. (#17749)
|
2 月之前 |
|
Xuan-Son Nguyen
|
2c453c6c77
convert: add error message for mistral3 quantized weight (#17686)
|
2 月之前 |
|
Xuan-Son Nguyen
|
cd3c118908
model: support Ministral3 (#17644)
|
2 月之前 |
 Piotr Wilkin (ilintar)
|
ff55414c42
model : Qwen3 Next (#16095)
|
2 月之前 |
 Aleksei Nikiforov
|
05872ac885
convert : fix big-endian conversion (#17431)
|
2 月之前 |
|
Sigbjørn Skjæret
|
b61de2b2df
convert : allow quantizing lora again (#17453)
|
2 月之前 |
 william pan
|
4902eebe33
models : Added support for RND1 Diffusion Language Model (#17433)
|
2 月之前 |
|
Sigbjørn Skjæret
|
07b0e7a5ac
convert : use self.block_count everywhere instead of reading hparams (#17359)
|
2 月之前 |
|
Sigbjørn Skjæret
|
662192e1dc
convert : remove unnecessary chat template patching (#17289)
|
2 月之前 |
|
Sigbjørn Skjæret
|
9a8860cf5d
convert : use all parts in safetensors index (#17286)
|
2 月之前 |
|
Sigbjørn Skjæret
|
9d3ef4809f
convert : set expert gating func in base class (#17279)
|
2 月之前 |
 Bartowski
|
e1fcf8b09b
model : add AfmoeForCausalLM support (#16477)
|
2 月之前 |
 levkropp
|
2fc392ce35
convert : register UMT5Model architecture for T5 conversion (#17160)
|
2 月之前 |
 compilade
|
802cef44bf
convert : parse safetensors directly (#15667)
|
3 月之前 |
|
compilade
|
1c07c0c68c
convert : handle compressed-tensors quant method (#17069)
|
3 月之前 |
 Li Pengzhan
|
9f052478c2
model : add openPangu-Embedded (#16941)
|
3 月之前 |
 Zhiyong Wang
|
6b9a52422b
model: add Janus Pro for image understanding (#16906)
|
3 月之前 |
|
Piotr Wilkin (ilintar)
|
0de0a01576
model : Minimax M2 (#16831)
|
3 月之前 |
 JJJYmmm
|
d261223d24
model: add support for qwen3vl series (#16780)
|
3 月之前 |
 Tianyue-Zhao
|
bacddc049a
model: Add support for CogVLM model (#15002)
|
3 月之前 |
|
Xuan-Son Nguyen
|
c55d53acec
model : add LightOnOCR-1B model (#16764)
|
3 月之前 |
|
Sigbjørn Skjæret
|
73a48c9790
convert : enable expert group selection for all models with it (#16691)
|
3 月之前 |
 Galunid
|
5d195f17bc
convert : handle mmproj filename/path properly (#16760)
|
3 月之前 |
|
compilade
|
5cca2542ac
convert : avoid dequantizing mxfp4 for GPT-OSS (#16756)
|
3 月之前 |
|
compilade
|
f8f071fadd
convert : handle pre-quantized models (#14810)
|
3 月之前 |
