 Georgi Gerganov
|
20fc3804bf
convert : fix gemma v1 tokenizer convert (#8248)
|
1 year ago |
 AidanBeltonS
|
f619024764
[SYCL] Remove unneeded semicolons (#8280)
|
1 year ago |
 Daniele
|
d23287f122
Define and optimize RDNA1 (#8085)
|
1 year ago |
 slaren
|
5f2d4e60e2
ppl : fix n_seq_max for perplexity (#8277)
|
1 year ago |
 Xuan Son Nguyen
|
916248af1f
fix phi 3 conversion (#8262)
|
1 year ago |
 Judd
|
f8d6a23804
fix typo (#8267)
|
1 year ago |
|
AidanBeltonS
|
fadde67135
Dequant improvements rebase (#8255)
|
1 year ago |
 MistApproach
|
a27152b602
fix: add missing short command line argument -mli for multiline-input (#8261)
|
1 year ago |
 Clint Herron
|
3e2618bc7b
Adding step to `clean` target to remove legacy binary names to reduce upgrade / migration confusion arising from #7809. (#8257)
|
1 year ago |
|
Clint Herron
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 year ago |
 Faisal Zaghloul
|
968967376d
Add `JAIS` model(s) (#8118)
|
1 year ago |
 Daniel Bevenius
|
023b8807e1
convert-hf : print output file name when completed (#8181)
|
1 year ago |
|
slaren
|
0e0590adab
cuda : update supports_op for matrix multiplication (#8245)
|
1 year ago |
 luoyu-intel
|
a9f3b10215
[SYCL] Fix win build conflict of math library (#8230)
|
1 year ago |
|
luoyu-intel
|
d08c20edde
[SYCL] Fix the sub group size of Intel (#8106)
|
1 year ago |
|
Xuan Son Nguyen
|
5fac350b9c
Fix gemma2 tokenizer convert (#8244)
|
1 year ago |
 Johannes Gäßler
|
cb5fad4c6c
CUDA: refactor and optimize IQ MMVQ (#8215)
|
1 year ago |
 Mateusz Charytoniuk
|
dae57a1ebc
readme: add Paddler to the list of projects (#8239)
|
1 year ago |
|
Xuan Son Nguyen
|
49122a873f
gemma2: add sliding window mask (#8227)
|
1 year ago |
 Roni
|
0ddeff1023
readme : update tool list (#8209)
|
1 year ago |
 Michael Francis
|
3840b6f593
nix : enable curl (#8043)
|
1 year ago |
|
Georgi Gerganov
|
257f8e41e2
nix : remove OpenCL remnants (#8235)
|
1 year ago |
 iacore
|
694c59cb42
Document BERT support. (#8205)
|
1 year ago |
 zhentaoyu
|
197fe6c1d7
[SYCL] Update SYCL-Rope op and Refactor (#8157)
|
1 year ago |
|
Georgi Gerganov
|
d0a7145ba9
flake.lock: Update (#8218)
|
1 year ago |
|
Xuan Son Nguyen
|
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
|
1 year ago |
 Andrei
|
1c5eba6f8e
llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197)
|
1 year ago |
|
Xuan Son Nguyen
|
72272b83a3
fix code typo in llama-cli (#8198)
|
1 year ago |
 Olivier Chafik
|
8748d8ac6f
json: attempt to skip slow tests when running under emulator (#8189)
|
1 year ago |
|
Xuan Son Nguyen
|
26a39bbd6b
Add MiniCPM, Deepseek V2 chat template + clean up `llama_chat_apply_template_internal` (#8172)
|
1 year ago |
