baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

runner.go: Don't try to extract image tags for text models

Browse source 
When processing a prompt, we look for image tags of the form
[img-0], which are inserted by the Ollama server process.
However, this can cause errors if the original prompt has these
tags - typically an image not found error is returned.

This changes tag searching behavior to be similar to the 0.3.x
series, which will largely avoid these problems. However,they can
still happen when input text with these tags is used with image
models. The correct solution is to escape the tags but this is a
larger issue with special sequences in general so this is an
incremental fix that should avoid the problem for the majority
of cases.
This commit is contained in:
Jesse Gross 2024-11-20 15:08:24 -08:00 committed by Jesse Gross
parent 2cd11ae365
commit 71e6a0d0d1
1 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
llama/runner/runner.go
View file

@ -164,10 +164,16 @@ func (s *Server) NewSequence(prompt string, images []ImageData, params NewSequen
// generating image embeddings for each image
func (s *Server) inputs(prompt string, images []ImageData) ([]input, error) {
var inputs []input
var parts []string
var matches [][]string
if s.image != nil {
re := regexp.MustCompile(`\[img-(\d+)\]`)
parts := re.Split(prompt, -1)
matches := re.FindAllStringSubmatch(prompt, -1)
parts = re.Split(prompt, -1)
matches = re.FindAllStringSubmatch(prompt, -1)
} else {
parts = []string{prompt}
}
for i, part := range parts {
// text - tokenize