diff --git a/docker-compose.yml b/docker-compose.yml index 366a616..47370e5 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -18,8 +18,8 @@ services: ports: - "8002:8000" command: > - --model microsoft/Phi-4 - --max_model_len 15000 + --model noxneural/Hermes-3-Llama-3.2-3B-awq-4-bit + --max_model_len 20000 --guided-decoding-backend outlines embeddings: