 Michael Yang
|
171eb040fc
simplify safetensors reading
|
hai 11 meses |
|
Michael Yang
|
bbbd9f20f3
cleanup
|
hai 1 ano |
|
Michael Yang
|
547132e820
bpe pretokenizer
|
hai 1 ano |
 Patrick Devine
|
c8cf0d94ed
llama3 conversion
|
hai 1 ano |
 Patrick Devine
|
14476d48cc
fixes for gguf (#3863)
|
hai 1 ano |
|
Michael Yang
|
e74163af4c
fix padding to only return padding
|
hai 1 ano |
|
Michael Yang
|
6d53b67c2c
Merge pull request #3663 from ollama/mxyng/fix-padding
|
hai 1 ano |
|
Michael Yang
|
969238b19e
fix padding in decode
|
hai 1 ano |
|
Patrick Devine
|
9f8691c6c8
Add llama2 / torch models for `ollama create` (#3607)
|
hai 1 ano |
|
Michael Yang
|
8b2c10061c
refactor tensor query
|
hai 1 ano |
|
Michael Yang
|
d338d70492
refactor model parsing
|
hai 1 ano |
|
Patrick Devine
|
5a5efee46b
Add gemma safetensors conversion (#3250)
|
hai 1 ano |
|
Patrick Devine
|
1b272d5bcd
change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347)
|
hai 1 ano |
|
Michael Yang
|
22f326464e
Merge pull request #3083 from ollama/mxyng/refactor-readseeker
|
hai 1 ano |
 Blake Mizerany
|
6ce37e4d96
llm,readline: use errors.Is instead of simple == check (#3161)
|
hai 1 ano |
|
Michael Yang
|
0085297928
refactor readseeker
|
hai 1 ano |
|
Michael Yang
|
76bdebbadf
decode ggla
|
hai 1 ano |
|
Patrick Devine
|
2c017ca441
Convert Safetensors to an Ollama model (#2824)
|
hai 1 ano |
|
Michael Yang
|
949d7b1c48
add gguf file types (#2532)
|
hai 1 ano |
|
Michael Yang
|
cd22855ef8
refactor tensor read
|
hai 1 ano |
|
Michael Yang
|
eaed6f8c45
add max context length check
|
hai 1 ano |
 Jeffrey Morgan
|
08f1e18965
Offload layers to GPU based on new model size estimates (#1850)
|
hai 1 ano |
|
Michael Yang
|
56ffc3023a
remove per-model types
|
hai 1 ano |
|
Michael Yang
|
5a5dca13b2
comments
|
hai 1 ano |
|
Michael Yang
|
72e7a49aa9
seek instead of copyn
|
hai 1 ano |
|
Michael Yang
|
2cb0fa7d40
split from into one or more models
|
hai 1 ano |
|
Michael Yang
|
199941cd15
fix: gguf int type
|
hai 1 ano |
|
Michael Yang
|
c5e1bbabda
instead of static number of parameters for each model family, get the real number from the tensors (#1022)
|
hai 1 ano |
|
Michael Yang
|
125d0a013a
ggufv3
|
hai 1 ano |
|
Michael Yang
|
c02c0cd483
starcoder
|
hai 1 ano |
