 Marcus Dunn
|
d5ab29757e
llama : constified `llama_set_state_data`'s `src` (#5774)
|
1 жил өмнө |
 Georgi Gerganov
|
08c5ee87e4
llama : remove deprecated API (#5770)
|
1 жил өмнө |
 compilade
|
adcb12a9ba
llama : fix non-quantization of expert gating tensors (#5754)
|
1 жил өмнө |
 Douglas Hanley
|
177628bfd8
llama : improve BERT tokenization (#5740)
|
1 жил өмнө |
 Kawrakow
|
0becb22ac0
IQ4_XS: a 4.25 bpw quantization (#5747)
|
1 жил өмнө |
|
Georgi Gerganov
|
9d533a77d0
llama : fix defrag bugs + add parameter (#5735)
|
1 жил өмнө |
|
Kawrakow
|
a33e6a0d2a
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)
|
1 жил өмнө |
 AidanBeltonS
|
e849078c6e
[SYCL] Add support for soft_max ALiBi (#5639)
|
1 жил өмнө |
|
Georgi Gerganov
|
269de86ba0
llama : fix Gemma rope type (#5691)
|
1 жил өмнө |
|
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
1 жил өмнө |
|
Georgi Gerganov
|
ab336a9d5e
code : normalize enum names (#5697)
|
1 жил өмнө |
|
Kawrakow
|
4c4cb30736
IQ3_S: a much better alternative to Q3_K (#5676)
|
1 жил өмнө |
 Jared Van Bortel
|
15499eb942
mpt : do not duplicate token_embd.weight on disk (#5670)
|
1 жил өмнө |
|
Georgi Gerganov
|
96633eeca1
gemma : use more bits for the token_embd.weight tensor (#5650)
|
1 жил өмнө |
|
Georgi Gerganov
|
847eedbdb2
py : add Gemma conversion from HF models (#5647)
|
1 жил өмнө |
 Xuan Son Nguyen
|
373ee3fbba
Add Gemma chat template (#5665)
|
1 жил өмнө |
|
Georgi Gerganov
|
3a03541ced
minor : fix trailing whitespace (#5638)
|
1 жил өмнө |
|
Xuan Son Nguyen
|
a46f50747b
server : fallback to chatml, add AlphaMonarch chat template (#5628)
|
1 жил өмнө |
 Dat Quoc Nguyen
|
4ef245a92a
mpt : add optional bias tensors (#5638)
|
1 жил өмнө |
 slaren
|
973053d8b0
llama : fix loading models with shared tok_embd and output (#5651)
|
1 жил өмнө |
|
slaren
|
7fe4678b02
llama : fix session save/load with quantized KV (#5649)
|
1 жил өмнө |
|
slaren
|
ba2135ccae
gemma : allow offloading the output tensor (#5646)
|
1 жил өмнө |
 postmasters
|
580111d42b
llama : add `gemma` model (#5631)
|
1 жил өмнө |
|
Kawrakow
|
a14679cc30
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)
|
1 жил өмнө |
|
Xuan Son Nguyen
|
9c405c9f9a
Server: use llama_chat_apply_template (#5593)
|
1 жил өмнө |
|
Georgi Gerganov
|
f53119cec4
minor : fix trailing whitespace (#5538)
|
1 жил өмнө |
|
Xuan Son Nguyen
|
11b12de39b
llama : add llama_chat_apply_template() (#5538)
|
1 жил өмнө |
|
Kawrakow
|
bd2d4e393b
1.5 bit quantization (#5453)
|
1 жил өмнө |
|
Georgi Gerganov
|
8f1be0d42f
ggml : add ALiBi support for ggml_soft_max_ext (#5488)
|
1 жил өмнө |
 Herman Semenov
|
65085c713e
llama : minor fixed return int value (#5529)
|
1 жил өмнө |
