 Michael Yang
|
6ffb5cb017
add conversion for microsoft phi 3 mini/medium 4k, 128
|
há 11 meses atrás |
|
Michael Yang
|
df993fa37b
comments
|
há 10 meses atrás |
|
Michael Yang
|
5e9db9fb0b
refactor convert
|
há 11 meses atrás |
|
Michael Yang
|
6b252918fb
update convert test to check result data
|
há 11 meses atrás |
|
Michael Yang
|
4a565cbf94
add chat and generate tests with mock runner
|
há 9 meses atrás |
 Blake Mizerany
|
cb42e607c5
llm: speed up gguf decoding by a lot (#5246)
|
há 10 meses atrás |
|
Michael Yang
|
7bdcd1da94
Revert "Merge pull request #4938 from ollama/mxyng/fix-byte-order"
|
há 10 meses atrás |
|
Michael Yang
|
620d5c569e
fix parsing big endian gguf
|
há 11 meses atrás |
|
Michael Yang
|
030e765e76
fix create model when template detection errors
|
há 11 meses atrás |
|
Michael Yang
|
e40145a39d
lint
|
há 11 meses atrás |
|
Michael Yang
|
171eb040fc
simplify safetensors reading
|
há 11 meses atrás |
|
Michael Yang
|
bbbd9f20f3
cleanup
|
há 11 meses atrás |
|
Michael Yang
|
547132e820
bpe pretokenizer
|
há 11 meses atrás |
 Patrick Devine
|
c8cf0d94ed
llama3 conversion
|
há 1 ano atrás |
 Patrick Devine
|
14476d48cc
fixes for gguf (#3863)
|
há 1 ano atrás |
|
Michael Yang
|
e74163af4c
fix padding to only return padding
|
há 1 ano atrás |
|
Michael Yang
|
6d53b67c2c
Merge pull request #3663 from ollama/mxyng/fix-padding
|
há 1 ano atrás |
|
Michael Yang
|
969238b19e
fix padding in decode
|
há 1 ano atrás |
|
Patrick Devine
|
9f8691c6c8
Add llama2 / torch models for `ollama create` (#3607)
|
há 1 ano atrás |
|
Michael Yang
|
8b2c10061c
refactor tensor query
|
há 1 ano atrás |
|
Michael Yang
|
d338d70492
refactor model parsing
|
há 1 ano atrás |
|
Patrick Devine
|
5a5efee46b
Add gemma safetensors conversion (#3250)
|
há 1 ano atrás |
|
Patrick Devine
|
1b272d5bcd
change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347)
|
há 1 ano atrás |
|
Michael Yang
|
22f326464e
Merge pull request #3083 from ollama/mxyng/refactor-readseeker
|
há 1 ano atrás |
|
Blake Mizerany
|
6ce37e4d96
llm,readline: use errors.Is instead of simple == check (#3161)
|
há 1 ano atrás |
|
Michael Yang
|
0085297928
refactor readseeker
|
há 1 ano atrás |
|
Michael Yang
|
76bdebbadf
decode ggla
|
há 1 ano atrás |
|
Patrick Devine
|
2c017ca441
Convert Safetensors to an Ollama model (#2824)
|
há 1 ano atrás |
|
Michael Yang
|
949d7b1c48
add gguf file types (#2532)
|
há 1 ano atrás |
|
Michael Yang
|
cd22855ef8
refactor tensor read
|
há 1 ano atrás |
