Sync from GitHub via hub-sync

VERSION

@@ -1 +1 @@
-3d3a30720c329276ef3638512b22d6c3fb1ea25f
+d41f44e05d8d4b3e36c81f2091e9f279a0ec4af5

hf_inference.py

@@ -0,0 +1,12 @@
+import os
+from huggingface_hub import InferenceClient
+
+# Initialize client with your model and token
+client = InferenceClient(
+    model="mistralai/Mistral-7B-Instruct-v0.3",
+    token=os.environ["HF_TOKEN"] # Recommended: set your token in env vars
+)
+
+# Example: Text Generation
+output = client.text_generation("What is the capital of France?")
+print(output)

smolagents/hellosmol.py

@@ -0,0 +1,17 @@
+import os
+from huggingface_hub import InferenceClient
+
+## You need a token from https://hf.co/settings/tokens, ensure that you select 'read' as the token type. If you run this on Google Colab, you can set it up in the "settings" tab under "secrets". Make sure to call it "HF_TOKEN"
+# HF_TOKEN = os.environ.get("HF_TOKEN")
+
+client = InferenceClient(model="moonshotai/Kimi-K2.5")
+
+output = client.chat.completions.create(
+    messages=[
+        {"role": "user", "content": "The capital of France is"},
+    ],
+    stream=False,
+    max_tokens=1024,
+    extra_body={'thinking': {'type': 'disabled'}},
+)
+print(output.choices[0].message.content)