Update app.py

app.py

@@ -6,13 +6,13 @@ from pynvml import *
 nvmlInit()
 gpu_h = nvmlDeviceGetHandleByIndex(0)
 ctx_limit = 3000
-title = "RWKV-5-World-7B-v2-20240128-ctx4096"
+title = "RWKV-v5-Eagle-World-7B-v2-20240128-ctx4096"
 
 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-5-world", filename=f"{title}.pth")
+model_path = hf_hub_download(repo_id="RWKV/v5-Eagle-7B", filename=f"{title}.pth")
 model = RWKV(model=model_path, strategy='cuda fp16i8 *8 -> cuda fp16')
 from rwkv.utils import PIPELINE, PIPELINE_ARGS
 pipeline = PIPELINE(model, "rwkv_vocab_v20230424")
@@ -21,19 +21,19 @@ def generate_prompt(instruction, input=""):
     instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
     input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
     if input:
-        return f"""Instruction: {instruction}
+        return f"""### Instruction: {instruction}
 
-Input: {input}
+### Input: {input}
 
-Response:"""
+### Response:"""
     else:
-        return f"""User: hi
+        return f"""### User: hi
 
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
+### Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
 
-User: {instruction}
+### User: {instruction}
 
-Assistant:"""
+### Assistant:"""
 
 def evaluate(
     ctx,