Rename Termite references to Antfly Inference

README.md

@@ -12,7 +12,7 @@ tags:
   - embeddings
   - feature-extraction
   - antfly
-  - termite
+  - antfly-inference
 pipeline_tag: feature-extraction
 datasets:
   - OpenSound/AudioCaps
@@ -22,7 +22,7 @@ datasets:
 
 CLIPCLAP is a unified multimodal embedding model that maps **text**, **images**, and **audio** into a shared 512-dimensional vector space. It combines OpenAI's [CLIP](https://huggingface.co/openai/clip-vit-base-patch32) (text + image) with LAION's [CLAP](https://huggingface.co/laion/larger_clap_music_and_speech) (audio) through a trained linear projection.
 
-Built by [antflydb](https://github.com/antflydb) for use with [Termite](https://github.com/antflydb/antfly/tree/main/termite), a standalone ML inference service for embeddings, chunking, and reranking.
+Built by [antflydb](https://github.com/antflydb) for use with [Antfly Inference](https://github.com/antflydb/antfly/tree/main/zig/pkg/inference), a standalone ML inference service for embeddings, chunking, reranking, and local model serving.
 
 ## Architecture
 
@@ -44,12 +44,12 @@ All three modalities produce **512-dimensional L2-normalized embeddings** that a
 - Cross-modal retrieval (find images from audio queries, audio from text, etc.)
 - Audio-visual content discovery
 
-## How to Use with Termite
+## How to Use with Antfly Inference
 
 ```bash
 # Pull and run the model
-termite pull clipclap
-termite run
+antfly inference pull antflydb/clipclap:gguf:Q4_K
+antfly inference run
 
 # Embed text
 curl -X POST http://localhost:8082/embed \