 Michael Yang
|
aee28501b5
Merge pull request #9661 from ollama/gemma
|
1 month ago |
 jmorganca
|
83f0ec8269
all: address linter errors
|
1 month ago |
|
jmorganca
|
c6b6938b3a
kvcache: fix tests by adding AvgPool2D stub
|
1 month ago |
|
jmorganca
|
fb4664fcec
model: add more spm tokenizer tests
|
1 month ago |
|
jmorganca
|
20e3593863
model: validate left and right pairs before merging them
|
1 month ago |
|
Michael Yang
|
63a394068c
use 2d pooling
|
1 month ago |
 Daniel Hiltgen
|
ab39e08eb9
llm: auto detect models that require Ollama Engine (#1)
|
1 month ago |
|
jmorganca
|
11bfa62796
add trailing \n\n after <end_of_image> to match reference implementation
|
1 month ago |
|
jmorganca
|
f63e62e546
reduce kernel size, add TODO for loading from config
|
1 month ago |
|
jmorganca
|
65b0f329d1
Revert "Allow models to force a new batch"
|
1 month ago |
 Jesse Gross
|
06007c0a18
Allow models to force a new batch
|
1 month ago |
|
Jesse Gross
|
a8e83a7654
Disable causal attention based on batch index
|
1 month ago |
|
Jesse Gross
|
475005504e
Restrict Gemma to a single image per request
|
1 month ago |
|
Jesse Gross
|
2c40c4d35e
Fix follow up images and images split across batches
|
1 month ago |
|
Michael Yang
|
e95278932b
use non-causal mask only for image positions
|
1 month ago |
|
Michael Yang
|
9d2a20a763
use non-causal mask for inputs with images
|
1 month ago |
 Patrick Devine
|
2e54d72fc3
fix gemma3 1b conversion
|
1 month ago |
|
Michael Yang
|
6b32a2d549
compat with upstream gguf
|
1 month ago |
|
Michael Yang
|
c5cbe4fc2a
fallback to cpu
|
1 month ago |
|
Michael Yang
|
f888912870
fix vision encoder
|
1 month ago |
|
Michael Yang
|
9e4642e9b3
ollama debug tensor
|
1 month ago |
|
Michael Yang
|
6b0486c216
duplicate token_embd to output
|
1 month ago |
|
Michael Yang
|
d368c039f0
skip repacking vision tensors
|
1 month ago |
|
Patrick Devine
|
9b54267e69
fix configs
|
1 month ago |
|
Michael Yang
|
46bb0169c4
update model
|
1 month ago |
|
Michael Yang
|
8934324b72
use fast attention
|
1 month ago |
|
Jesse Gross
|
0e886595bf
Fix tests and drift from main
|
1 month ago |
|
Patrick Devine
|
c62861f4fa
fix conversion
|
1 month ago |
|
Michael Yang
|
0df1800436
set non-causal attention
|
1 month ago |
|
Patrick Devine
|
631fecc6d9
temporary work around for converting spm
|
1 month ago |
