Upload 2 files

README.md

@@ -36,7 +36,11 @@ itself.
 To run it (locally or as a Space), set the `HF_TOKEN` secret/env var to a
 Hugging Face access token with Inference API permission. Optionally set
 `HF_AGENT_MODEL` to override the default model
-(`Qwen/Qwen2.5-Coder-32B-Instruct`), and `HF_AGENT_PROVIDER` to override the
+(`meta-llama/Llama-3.3-70B-Instruct`), and `HF_AGENT_PROVIDER` to override the
 default Inference Provider (`together`) — pinned explicitly because the
 router's `auto` selection can land on a provider that doesn't support tool
-calling for a given model (HTTP 422 `UNSUPPORTED_OPENAI_PARAMS`).
+calling for a given model (HTTP 422 `UNSUPPORTED_OPENAI_PARAMS`), and not every
+provider hosts every model (HTTP 4xx "Model ... is not supported by provider
+..."). Check `https://router.huggingface.co/v1/models/<repo_id>` to see which
+providers host a given model and whether they support tools before changing
+either variable.

agent.py

@@ -30,7 +30,7 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # Any HF Inference API model that supports tool calling works here. Override via the
 # HF_AGENT_MODEL env var without touching code.
-HF_MODEL_REPO_ID = os.getenv("HF_AGENT_MODEL", "Qwen/Qwen2.5-Coder-32B-Instruct")
+HF_MODEL_REPO_ID = os.getenv("HF_AGENT_MODEL", "meta-llama/Llama-3.3-70B-Instruct")
 
 # Left unset ("auto"), the HF router picks whichever provider is cheapest/fastest for the
 # model, and some of those don't support the `tools` param at all (HTTP 422