Fix Inference,Env: Change Model

.env

@@ -1,4 +1,4 @@
 HF_TOKEN=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
 API_BASE_URL=https://api.groq.com/openai/v1
-MODEL_NAME=llama3-8b-8192
+MODEL_NAME=llama-3.1-70b-versatile
 ENV_BASE_URL=https://therubberduckdebuggers-cascade-containment.hf.space

inference.py

@@ -32,7 +32,7 @@ from core.policy_update import compute_advantage, update_memory
 # ── Configuration ─────────────────────────────────────────────────────────────
 
 API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
-MODEL_NAME   = os.getenv("MODEL_NAME",   "meta-llama/llama3-8b-8192")
+MODEL_NAME   = os.getenv("MODEL_NAME",   "meta-llama/llama-3.1-70b-versatile")
 ENV_BASE_URL = os.getenv("ENV_BASE_URL", "http://localhost:7860")
 BENCHMARK    = "cascade-containment"