fix: use fp32 models consistently everywhere to ensure compatibility

Changed default dtype from q8 to fp32 across all embedding implementations:
- embedding.ts: Default dtype changed to fp32
- worker-embedding.ts: Use fp32 for consistency
- universal-memory-manager.ts: Use fp32 for consistency
- lightweight-embedder.ts: Use fp32 for consistency
- hybridModelManager.ts: Use fp32 for all configurations

This ensures we use the exact same model (model.onnx) everywhere,
maintaining data compatibility and avoiding 404 errors for quantized models.

src/embeddings/lightweight-embedder.ts

@@ -113,7 +113,7 @@ export class LightweightEmbedder {
       console.log('⚠️ Loading ONNX model for complex text...')
       const { TransformerEmbedding } = await import('../utils/embedding.js')
       this.onnxEmbedder = new TransformerEmbedding({ 
-        dtype: 'q8',
+        dtype: 'fp32',
         verbose: false 
       })
       await this.onnxEmbedder.init()

src/embeddings/universal-memory-manager.ts

@@ -139,7 +139,7 @@ export class UniversalMemoryManager {
       
       this.embeddingFunction = new TransformerEmbedding({
         verbose: false,
-        dtype: 'q8',
+        dtype: 'fp32',
         localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
       })
       

src/embeddings/worker-embedding.ts

@@ -16,7 +16,7 @@ async function initModel(): Promise<void> {
   if (!model) {
     model = new TransformerEmbedding({
       verbose: false,
-      dtype: 'q8',
+      dtype: 'fp32',
       localFilesOnly: process.env.BRAINY_ALLOW_REMOTE_MODELS !== 'true'
     })
     await model.init()