Black formatting

examples/fastapi_server.py

@@ -5,9 +5,11 @@ from llama_cpp import Llama
 from fastapi import FastAPI
 from pydantic import BaseModel, BaseSettings, Field
 
+
 class Settings(BaseSettings):
     model: str
 
+
 app = FastAPI(
     title="🦙 llama.cpp Python API",
     version="0.0.1",
@@ -15,6 +17,7 @@ app = FastAPI(
 settings = Settings()
 llama = Llama(settings.model)
 
+
 class CompletionRequest(BaseModel):
     prompt: str
     suffix: Optional[str] = Field(None)
@@ -31,12 +34,11 @@ class CompletionRequest(BaseModel):
         schema_extra = {
             "example": {
                 "prompt": "\n\n### Instructions:\nWhat is the capital of France?\n\n### Response:\n",
-                "stop": ["\n", "###"]
+                "stop": ["\n", "###"],
             }
         }
 
 
-
 @app.post("/v1/completions")
 def completions(request: CompletionRequest):
-    return llama(**request.dict())
+    return llama(**request.dict())

examples/high_level_api_basic_inference.py

@@ -9,6 +9,11 @@ args = parser.parse_args()
 
 llm = Llama(model_path=args.model)
 
-output = llm("Question: What are the names of the planets in the solar system? Answer: ", max_tokens=48, stop=["Q:", "\n"], echo=True)
+output = llm(
+    "Question: What are the names of the planets in the solar system? Answer: ",
+    max_tokens=48,
+    stop=["Q:", "\n"],
+    echo=True,
+)
 
-print(json.dumps(output, indent=2))
+print(json.dumps(output, indent=2))

examples/langchain_custom_llm.py

@@ -5,6 +5,7 @@ from llama_cpp import Llama
 from langchain.llms.base import LLM
 from typing import Optional, List, Mapping, Any
 
+
 class LlamaLLM(LLM):
     model_path: str
     llm: Llama
@@ -16,7 +17,7 @@ class LlamaLLM(LLM):
     def __init__(self, model_path: str, **kwargs: Any):
         model_path = model_path
         llm = Llama(model_path=model_path)
-        super().__init__(model_path=model_path, llm=llm,  **kwargs)
+        super().__init__(model_path=model_path, llm=llm, **kwargs)
 
     def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
         response = self.llm(prompt, stop=stop or [])
@@ -26,6 +27,7 @@ class LlamaLLM(LLM):
     def _identifying_params(self) -> Mapping[str, Any]:
         return {"model_path": self.model_path}
 
+
 parser = argparse.ArgumentParser()
 parser.add_argument("-m", "--model", type=str, default="./models/...")
 args = parser.parse_args()
@@ -34,7 +36,9 @@ args = parser.parse_args()
 llm = LlamaLLM(model_path=args.model)
 
 # Basic Q&A
-answer = llm("Question: What is the capital of France? Answer: ", stop=["Question:", "\n"])
+answer = llm(
+    "Question: What is the capital of France? Answer: ", stop=["Question:", "\n"]
+)
 print(f"Answer: {answer.strip()}")
 
 # Using in a chain
@@ -48,4 +52,4 @@ prompt = PromptTemplate(
 chain = LLMChain(llm=llm, prompt=prompt)
 
 # Run the chain only specifying the input variable.
-print(chain.run("colorful socks"))
+print(chain.run("colorful socks"))

examples/low_level_api_inference.py

@@ -27,7 +27,15 @@ embd = embd_inp
 n = 8
 
 for i in range(n):
-    id = llama_cpp.llama_sample_top_p_top_k(ctx, (llama_cpp.c_int * len(embd))(*embd), n_of_tok + i, 40, 0.8, 0.2, 1.0/0.85)
+    id = llama_cpp.llama_sample_top_p_top_k(
+        ctx,
+        (llama_cpp.c_int * len(embd))(*embd),
+        n_of_tok + i,
+        40,
+        0.8,
+        0.2,
+        1.0 / 0.85,
+    )
 
     embd.append(id)
 
@@ -38,4 +46,4 @@ for i in range(n):
 
 llama_cpp.llama_free(ctx)
 
-print(prediction.decode("utf-8"))
+print(prediction.decode("utf-8"))