highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 12:07:39 +01:00
Code Issues Packages Projects Releases Wiki Activity

Qwen3VL Cloud Parser and Renderer (#12526)

Browse Source 
* working (other than tool call is the incorrect order) for tool calls and tools

* Tests work, other than image tags (tests do not go through server) and tools (not in the correct order, but contents are the same)

* testing for qwen3vl parser - toolparser is working

* made changes to JSON tool parser, wraps the TollCallFunction with a TollCall object

* Working parser for thinking models - assumes state of thinking, emits unambiguous content in thinking, does not call tool call in thinking

* changed the parser to start with collecting content

* thinking prefill

* add hasThinkingSupport parameter to parser

* qwen3-vl -> qwen3-vl-instruct for renderer/parser

* Add hasThinkingSupport=false to QwenVLParser

---------

Co-authored-by: Devon Rifkin <drifkin@drifkin.net>
This commit is contained in:
Grace
2025-10-13 16:52:33 -07:00
committed by GitHub
parent 4987f13d34
commit 05982a95cb
16 changed files with 2654 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
model/renderers/qwen3coder.go
View File

@@ -55,7 +55,9 @@ func renderAdditionalKeys(obj any, handledKeys map[string]bool) string {
return sb.String()
}
func Qwen3CoderRenderer(messages []api.Message, tools []api.Tool, _ *api.ThinkValue) (string, error) {
type Qwen3CoderRenderer struct{}
func (r *Qwen3CoderRenderer) Render(messages []api.Message, tools []api.Tool, _ *api.ThinkValue) (string, error) {
var sb strings.Builder
// filter out system messages and choose the first (if any) to win