Update app.py

app.py

@@ -6,7 +6,7 @@ from pynvml import *
 nvmlInit()
 gpu_h = nvmlDeviceGetHandleByIndex(0)
 ctx_limit = 2048
-title = "RWKV-4-Pile-14B-20230228-ctx4096-test663"
+title = "RWKV-4-Pile-14B-20230313-ctx8192-test1050"
 desc = f'''Links:
 <a href='https://github.com/BlinkDL/ChatRWKV' target="_blank" style="margin:0 0.5em">ChatRWKV</a>
 <a href='https://github.com/BlinkDL/RWKV-LM' target="_blank" style="margin:0 0.5em">RWKV-LM</a>
@@ -17,7 +17,7 @@ os.environ["RWKV_JIT_ON"] = '1'
 os.environ["RWKV_CUDA_ON"] = '1' # 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-pile-14b", filename="RWKV-4-Pile-14B-20230228-ctx4096-test663.pth")
+model_path = hf_hub_download(repo_id="BlinkDL/rwkv-4-pile-14b", filename=f"{title}.pth")
 model = RWKV(model=model_path, strategy='cuda fp16i8 *20 -> cuda fp16')
 from rwkv.utils import PIPELINE, PIPELINE_ARGS
 pipeline = PIPELINE(model, "20B_tokenizer.json")