readme: drop 'this model' qualifiers; move RAG use cases under Model details

README.md

@@ -48,15 +48,22 @@ license_link: LICENSE
 
 # LFM2.5-ColBERT-350M
 
-Two new multilingual retrieval models built on the bidirectional LFM2.5 backbone: **LFM2.5-ColBERT-350M** (this model), a late-interaction retriever, and **[LFM2.5-Embedding-350M](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M)**, a dense bi-encoder. Both are 350M params, the first bidirectional members of the LFM family, and target fast, cheap, and reliable multilingual / cross-lingual search across 11 languages — well-suited for short-context use cases like product catalogs, FAQs, and support docs.
+Two new multilingual retrieval models built on the bidirectional LFM2.5 backbone: **LFM2.5-ColBERT-350M**, a late-interaction retriever, and **[LFM2.5-Embedding-350M](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M)**, a dense bi-encoder. Both are 350M params and the first bidirectional members of the LFM family, targeting fast, cheap, and reliable multilingual / cross-lingual search across 11 languages.
 
 - **[LFM2.5-Embedding-350M](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M)** — one vector per document. Smallest, fastest index.
-- **LFM2.5-ColBERT-350M** (this model) — one vector per *token*, matched via MaxSim. Higher accuracy and better generalization at the cost of index size.
+- **LFM2.5-ColBERT-350M** — one vector per *token*, matched via MaxSim. Higher accuracy and better generalization at the cost of index size.
 
 For the full story on architecture (bidirectional patches over LFM2.5), training recipe, and benchmarks, see the [release blog post](https://www.liquid.ai/blog) *(link to be added)*.
 
 ## 📄 Model details
 
+We recommend LFM2.5-ColBERT-350M for short-context retrieval use cases, such as:
+
+- **E-commerce**: find products across many languages with semantic search at scale.
+- **FAQ and support knowledge bases**: retrieve the right answer reliably across customer-facing surfaces.
+- **On-device semantic search**: search files, emails, and notes locally on consumer hardware.
+- **Enterprise knowledge assistants**: retrieve internal legal, financial, and technical documents across languages.
+
 | Property              | **LFM2.5-ColBERT-350M**                | **[LFM2.5-Embedding-350M](https://huggingface.co/LiquidAI/LFM2.5-Embedding-350M)** |
 | --------------------- | -------------------------------------- | ----------------------------------- |
 | **Type**              | Late interaction (per-token vectors)   | Dense bi-encoder (single vector)    |