first commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tinyllama-1.1b-chat.gguf filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.9
+
+WORKDIR /code
+
+ENV HF_HOME=/code/.cache
+
+COPY ./requirements.txt /code/requirements.txt
+COPY ./main.py /code/main.py
+COPY ./tinyllama-1.1b-chat.gguf ./tinyllama-1.1b-chat.gguf
+
+RUN mkdir -p /code/.cache && chmod -R 777 /code/.cache
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,19 @@
+from fastapi import FastAPI
+import requests
+from llama_cpp import Llama 
+
+app = FastAPI()
+
+llm = Llama(model_path="./tinyllama-1.1b-chat.gguf")
+
+@app.post("/llm")
+async def stream(item: dict):
+	
+    if 'prompt' not in item.keys():
+        raise ValueError("prompt é obrigatório")
+
+    prompt = item['prompt']
+    temperatura = item['temperatura'] if 'temperatura' in item.keys() else 0.2
+    max_tokens = item['max_tokens'] if 'max_tokens' in item.keys() else 512
+    
+    return llm(prompt, max_tokens=max_tokens, temperature=temperatura)

requirements.txt

@@ -0,0 +1,3 @@
+llama-cpp-python
+langchain
+fastapi

tinyllama-1.1b-chat.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fecc3b3cd76bba89d504f29b616eedf7da85b96540e490ca5824d3f7d2776a0
+size 668788096