mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Reapply "add truncate and shift parameters" (#12582)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-10-11 16:06:14 -07:00
committed by GitHub
parent 5db8a818a1
commit 6544e14735
8 changed files with 298 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
server/prompt.go
View File

@@ -20,7 +20,7 @@ type tokenizeFunc func(context.Context, string) ([]int, error)
// chatPrompt accepts a list of messages and returns the prompt and images that should be used for the next chat turn.
// chatPrompt truncates any messages that exceed the context window of the model, making sure to always include 1) the
// latest message and 2) system messages
func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message, tools []api.Tool, think *api.ThinkValue) (prompt string, images []llm.ImageData, _ error) {
func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.Options, msgs []api.Message, tools []api.Tool, think *api.ThinkValue, truncate bool) (prompt string, images []llm.ImageData, _ error) {
var system []api.Message
// TODO: Ideally we would compute this from the projector metadata but some pieces are implementation dependent
@@ -59,7 +59,7 @@ func chatPrompt(ctx context.Context, m *Model, tokenize tokenizeFunc, opts *api.
}
}
if ctxLen > opts.NumCtx {
if truncate && ctxLen > opts.NumCtx {
slog.Debug("truncating input messages which exceed context length", "truncated", len(msgs[i:]))
break
} else {