 Josh Yan
|
309307c8f9
update test, remove comments
|
10 months ago |
 Josh
|
d069cf753b
Merge branch 'main' into jyan/reord-g
|
10 months ago |
|
Josh Yan
|
64405525b4
clean up
|
10 months ago |
|
Josh Yan
|
6ee22d5080
clean
|
10 months ago |
|
Josh Yan
|
873f334783
IT WORKS
|
10 months ago |
|
Josh Yan
|
fa49bfc0bd
FIXED TESTS
|
10 months ago |
 Michael Yang
|
4a565cbf94
add chat and generate tests with mock runner
|
10 months ago |
|
Josh Yan
|
25be20949c
test
|
10 months ago |
|
Josh Yan
|
40c0f9612e
unneccesary
|
10 months ago |
|
Josh Yan
|
15a0215203
running
|
10 months ago |
|
Josh Yan
|
faa3c937cf
writeto
|
10 months ago |
|
Josh Yan
|
cf57246aba
write
|
10 months ago |
|
Josh Yan
|
6fafe4f753
gguf
|
10 months ago |
|
Josh Yan
|
d7c8d4f3f4
ggufwritekv
|
10 months ago |
|
Josh Yan
|
3d0fd31f0e
TensorWriter
|
10 months ago |
|
Josh Yan
|
e75fb73839
types
|
10 months ago |
|
Josh Yan
|
2fdebffc8d
sawp
|
10 months ago |
|
Josh Yan
|
29ecfe493b
write
|
10 months ago |
 Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
11 months ago |
|
Michael Yang
|
7bdcd1da94
Revert "Merge pull request #4938 from ollama/mxyng/fix-byte-order"
|
11 months ago |
|
Michael Yang
|
620d5c569e
fix parsing big endian gguf
|
11 months ago |
|
Michael Yang
|
030e765e76
fix create model when template detection errors
|
11 months ago |
|
Michael Yang
|
e40145a39d
lint
|
1 year ago |
|
Michael Yang
|
171eb040fc
simplify safetensors reading
|
1 year ago |
|
Michael Yang
|
bbbd9f20f3
cleanup
|
1 year ago |
|
Michael Yang
|
547132e820
bpe pretokenizer
|
1 year ago |
 Patrick Devine
|
c8cf0d94ed
llama3 conversion
|
1 year ago |
 Patrick Devine
|
14476d48cc
fixes for gguf (#3863)
|
1 year ago |
|
Michael Yang
|
e74163af4c
fix padding to only return padding
|
1 year ago |
|
Michael Yang
|
6d53b67c2c
Merge pull request #3663 from ollama/mxyng/fix-padding
|
1 year ago |
