MrAli commited on
Commit
ec92ffb
·
verified ·
1 Parent(s): 65c3a8f

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +7 -8
app.py CHANGED
@@ -4,16 +4,8 @@ from huggingface_hub import hf_hub_download
4
  import os
5
  import requests
6
 
7
- os.system("ulimit -l unlimited")
8
-
9
  app = FastAPI()
10
 
11
- hf_hub_download("TheBloke/deepseek-coder-1.3b-base-GGUF", "deepseek-coder-1.3b-base.Q5_K_M.gguf", local_dir="./")
12
-
13
- model_l = Llama(model_path="./deepseek-coder-1.3b-base.Q5_K_M.gguf", n_ctx=16192, n_gpu_layers=0, n_threads=2, use_mlock=True)
14
-
15
- total = 0
16
-
17
  @app.post("/api")
18
  async def completion(request: Request):
19
  try:
@@ -38,5 +30,12 @@ async def completion(request: Request):
38
 
39
 
40
  if __name__ == "__main__":
 
 
 
 
 
 
 
41
  import uvicorn
42
  uvicorn.run(app, host="0.0.0.0", port=7860)
 
4
  import os
5
  import requests
6
 
 
 
7
  app = FastAPI()
8
 
 
 
 
 
 
 
9
  @app.post("/api")
10
  async def completion(request: Request):
11
  try:
 
30
 
31
 
32
  if __name__ == "__main__":
33
+ os.system("ulimit -l unlimited")
34
+
35
+ hf_hub_download("TheBloke/deepseek-coder-1.3b-base-GGUF", "deepseek-coder-1.3b-base.Q5_K_M.gguf", local_dir="./")
36
+
37
+ model_l = Llama(model_path="./deepseek-coder-1.3b-base.Q5_K_M.gguf", n_ctx=16192, n_gpu_layers=0, n_threads=2, use_mlock=True)
38
+
39
+ total = 0
40
  import uvicorn
41
  uvicorn.run(app, host="0.0.0.0", port=7860)