Update README.md

README.md

@@ -20,7 +20,7 @@ from huggingface_hub import snapshot_download
 from vllm import LLM, SamplingParams
 
 # Consider toggling "enforce_eager" to False if you want to load the model quicker, at the expense of tokens per second.
-repo = snapshot_download(repo_id="Staticaliza/Reya-Reasoning-8B-Distilled-GPTQ-Int4", allow_patterns=["*.json", "*.bin", "*.safetensors"])
+repo = snapshot_download(repo_id="Staticaliza/Reya-Reasoning", allow_patterns=["*.json", "*.bin", "*.safetensors"])
 llm = LLM(model=repo, dtype="auto", tensor_parallel_size=torch.cuda.device_count(), enforce_eager=True, trust_remote_code=True)
 
 params = SamplingParams(