mirror of
https://github.com/ollama/ollama.git
synced 2026-04-18 00:54:05 +02:00
cmd: fix context limits for droid and add qwen3-coder-next ctx (#14112)
This commit is contained in:
@@ -1,6 +1,7 @@
|
||||
package config
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"os"
|
||||
@@ -8,6 +9,7 @@ import (
|
||||
"path/filepath"
|
||||
"slices"
|
||||
|
||||
"github.com/ollama/ollama/api"
|
||||
"github.com/ollama/ollama/envconfig"
|
||||
)
|
||||
|
||||
@@ -112,9 +114,17 @@ func (d *Droid) Edit(models []string) error {
|
||||
}
|
||||
|
||||
// Build new Ollama model entries with sequential indices (0, 1, 2, ...)
|
||||
client, _ := api.ClientFromEnvironment()
|
||||
|
||||
var newModels []any
|
||||
var defaultModelID string
|
||||
for i, model := range models {
|
||||
maxOutput := 64000
|
||||
if isCloudModel(context.Background(), client, model) {
|
||||
if l, ok := lookupCloudModelLimit(model); ok {
|
||||
maxOutput = l.Output
|
||||
}
|
||||
}
|
||||
modelID := fmt.Sprintf("custom:%s-%d", model, i)
|
||||
newModels = append(newModels, modelEntry{
|
||||
Model: model,
|
||||
@@ -122,7 +132,7 @@ func (d *Droid) Edit(models []string) error {
|
||||
BaseURL: envconfig.Host().String() + "/v1",
|
||||
APIKey: "ollama",
|
||||
Provider: "generic-chat-completion-api",
|
||||
MaxOutputTokens: 64000,
|
||||
MaxOutputTokens: maxOutput,
|
||||
SupportsImages: false,
|
||||
ID: modelID,
|
||||
Index: i,
|
||||
|
||||
Reference in New Issue
Block a user