 Xuan Son Nguyen
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 年之前 |
 Icecream95
|
d7fd29fff1
llama : add OpenELM support (#7359)
|
1 年之前 |
|
Xuan Son Nguyen
|
49122a873f
gemma2: add sliding window mask (#8227)
|
1 年之前 |
 Andrei
|
1c5eba6f8e
llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197)
|
1 年之前 |
 Christian Zhou-Zheng
|
52fc8705a0
Option to split during conversion (#6942)
|
1 年之前 |
 fairydreaming
|
de0d6a68ac
gguf-py, convert-hf : model conversion support for T5 and FLAN-T5 model variants (#5763)
|
1 年之前 |
 Ștefan-Gabriel Muscalu
|
a94e6ff877
update: support Qwen2-57B-A14B (#7835)
|
1 年之前 |
 compilade
|
ed9f252118
gguf-py : decouple adding metadata from writing in GGUFWriter (#7827)
|
1 年之前 |
|
fairydreaming
|
ee3dff6b8e
Add support for DeepseekV2ForCausalLM (#7519)
|
1 年之前 |
|
compilade
|
b83bab15a5
gguf-py : fix and simplify quantized shape round-trip (#7483)
|
1 年之前 |
 liuwei-git
|
201cc11afa
llama : add phi3 128K model support (#7225)
|
1 年之前 |
|
compilade
|
ee52225067
convert-hf : support direct Q8_0 conversion (#7234)
|
1 年之前 |
|
compilade
|
5a419926b0
convert-hf : support bfloat16 conversion (#7158)
|
1 年之前 |
|
compilade
|
f98eb31c51
convert-hf : save memory with lazy evaluation (#7075)
|
1 年之前 |
 Brian
|
a2ac89d6ef
convert.py : add python logging instead of print() (#6511)
|
1 年之前 |
 Georgi Gerganov
|
f4ab2a4147
llama : fix BPE pre-tokenization (#6920)
|
1 年之前 |
|
Xuan Son Nguyen
|
7bb36ccf91
gguf : enforce that tensor names are unique (#6905)
|
1 年之前 |
 Sigbjørn Skjæret
|
03c0946d73
convert : support models with multiple chat templates (#6588)
|
1 年之前 |
 Daniel Bevenius
|
4fbd8098e6
gguf : add special tokens metadata for FIM/Infill (#6689)
|
1 年之前 |
|
Brian
|
a8bd14d557
gguf.py : add licence and version to gguf writer (#6504)
|
1 年之前 |
 Andrew Canis
|
12247f4c69
llama : add Command-R support (#6033)
|
1 年之前 |
 Ondřej Čertík
|
7ce2c77f88
gguf : add support for I64 and F64 arrays (#6062)
|
1 年之前 |
 Michael Podvitskiy
|
69ff61397d
llama : support models without vocabulary (#5798)
|
1 年之前 |
|
Georgi Gerganov
|
77178eedc8
gguf-py : fix dtype check (#6045)
|
1 年之前 |
|
Ondřej Čertík
|
3ca23481dd
gguf-py : add support for I8, I16 and I32 (#6045)
|
1 年之前 |
 compilade
|
c2101a2e90
llama : support Mamba Selective State Space Models (#5328)
|
1 年之前 |
 Jared Van Bortel
|
c7a0ad8ec9
convert-hf : make model class definitions self-contained (#5825)
|
1 年之前 |
 Douglas Hanley
|
4524290e87
Use correct type of pooling for embedding models (#5500)
|
1 年之前 |
 Michaël de Vries
|
73122473ff
fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false (#5487)
|
1 年之前 |
|
Douglas Hanley
|
03bf161eb6
llama : support batched embeddings (#5466)
|
1 年之前 |
