Update app.py

app.py

@@ -5,15 +5,14 @@ from huggingface_hub import hf_hub_download
 from pynvml import *
 nvmlInit()
 gpu_h = nvmlDeviceGetHandleByIndex(0)
-ctx_limit = 1536
-title = "RWKV-4-World-7B-v1-20230626-ctx4096"
-
+ctx_limit = 512
+title = "RWKV-4-World-0.4B-v1-20230529-ctx4096"
 os.environ["RWKV_JIT_ON"] = '1'
-os.environ["RWKV_CUDA_ON"] = '1' # if '1' then use CUDA kernel for seq mode (much faster)
+os.environ["RWKV_CUDA_ON"] = '0' # if '1' then use CUDA kernel for seq mode (much faster)
 
 from rwkv.model import RWKV
 model_path = hf_hub_download(repo_id="BlinkDL/rwkv-4-world", filename=f"{title}.pth")
-model = RWKV(model=model_path, strategy='cuda fp16i8 *8 -> cuda fp16')
+model = RWKV(model=model_path, strategy='cpu')
 from rwkv.utils import PIPELINE, PIPELINE_ARGS
 pipeline = PIPELINE(model, "rwkv_vocab_v20230424")