fix(ai): use correct llama.cpp model name
- Update model to qwen2.5-coder-32b-instruct-Q4_K_M - Match actual model available in llama.cpp on port 8081 Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
@@ -40,7 +40,7 @@ export async function POST(request: NextRequest) {
|
||||
let res: Awaited<ReturnType<typeof client.chat.completions.create>>
|
||||
try {
|
||||
res = await client.chat.completions.create({
|
||||
model: 'qwen2.5-coder-8k:latest',
|
||||
model: 'qwen2.5-coder-32b-instruct-Q4_K_M',
|
||||
max_tokens: 1024,
|
||||
messages: [
|
||||
{
|
||||
@@ -87,7 +87,7 @@ Scoring criteria: specificity (location, time, persons involved), completeness (
|
||||
|
||||
await withUser(session.sub, async tx => {
|
||||
await writeAuditLog(tx, 'incidents', session.sub, 'ai_quality_check', {
|
||||
score: input.score, passes: input.passes, model: 'qwen2.5-coder-8k:latest',
|
||||
score: input.score, passes: input.passes, model: 'qwen2.5-coder-32b-instruct-Q4_K_M',
|
||||
})
|
||||
})
|
||||
|
||||
|
||||
Reference in New Issue
Block a user