Add air-gapped usage for embedding using vLLM 0.20.0 and above

README.md

@@ -4650,6 +4650,20 @@ The **gte-multilingual-base** model is the latest in the [GTE](https://huggingfa
 - Embedding Dimension: 768
 - Max Input Tokens: 8192
 
+## Usage Air-Gapped
+
+> Tested with **vLLM 0.20.0**  and above.
+
+- Set `HF_HOME` to a temp directory, eg: `/tmp/hf`
+    - **OR** set `HF_MODULES_CACHE` to `/tmp/hf-modules-cache`. (we need this to stage `configuration.py` and `modeling.py` from the root dir [Reference](https://github.com/huggingface/transformers/blob/4e9f6fc67ce6290b3ab6efe2ddb1fcfc3e554382/src/transformers/dynamic_module_utils.py#L35-L47))
+- Set env var `HF_HUB_OFFLINE=1`
+
+```bash
+vllm serve yankexe/gte-multilingual-base-air-gapped \
+  --hf-overrides='{"architectures":["GteNewModel"]}' \
+  --runner=pooling \
+  --trust-remote-code
+```
 
 ## Usage 
 
@@ -4851,4 +4865,4 @@ If you find our paper or models helpful, please consider cite:
   pages={1393--1412},
   year={2024}
 }
-```
+```