Upload README.md with huggingface_hub

README.md

@@ -47,9 +47,12 @@ Combines multitask intent modeling, supervised IAB content classification, and p
 
 ```python
 !pip -q install -U pip
-!pip -q install -U "torch>=2.0.0" "transformers>=4.36.0" "huggingface_hub>=0.20.0" "safetensors>=0.4.0"
+!pip -q install -U "torch==2.10.0" "torchvision==0.25.0" "torchaudio==2.10.0"
+!pip -q install -U "transformers>=4.36.0" "huggingface_hub>=0.20.0" "safetensors>=0.4.0"
 ```
 
+Restart the runtime after installs (**Runtime → Restart runtime**) so the new Torch version is actually used.
+
 ```python
 from transformers import pipeline
 
@@ -66,6 +69,20 @@ print(out["model_output"]["classification"]["intent"])
 
 ---
 
+## Latency / inference timing (quick check)
+
+The first call includes model/code loading. Warm up once, then measure:
+
+```python
+import time
+q = "Which laptop should I buy for college?"
+
+_ = clf("warm up")
+t0 = time.perf_counter()
+out = clf(q)
+print(f"latency_ms={(time.perf_counter() - t0) * 1000:.1f}")
+```
+
 ### 1. `transformers.pipeline()` — anywhere (Python)
 
 ```python