implement endpoint

.gitignore

@@ -0,0 +1 @@
+.idea

app.py

@@ -0,0 +1,50 @@
+import os
+import urllib.request
+import gradio as gr
+from llama_cpp import Llama
+
+
+def download_file(file_link, filename):
+    # Checks if the file already exists before downloading
+    if not os.path.isfile(filename):
+        urllib.request.urlretrieve(file_link, filename)
+        print("File downloaded successfully.")
+    else:
+        print("File already exists.")
+
+
+# Dowloading GGML model from HuggingFace
+ggml_model_path = "https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/resolve/main/ggml-vicuna-7b-1.1-q4_1.bin"
+filename = "ggml-vicuna-7b-1.1-q4_1.bin"
+
+download_file(ggml_model_path, filename)
+
+
+llm = Llama(model_path=filename, n_ctx=512, n_batch=126)
+
+
+def generate_text(prompt="Who is the CEO of Apple?"):
+    output = llm(
+        prompt,
+        max_tokens=256,
+        temperature=0.1,
+        top_p=0.5,
+        echo=False,
+        stop=["#"],
+    )
+    output_text = output["choices"][0]["text"].strip()
+
+    # Remove Prompt Echo from Generated Text
+    cleaned_output_text = output_text.replace(prompt, "")
+    return cleaned_output_text
+
+
+description = "Vicuna-7B"
+
+gradio_interface = gr.Interface(
+    fn=generate_text,
+    inputs="text",
+    outputs="text",
+    title="Vicuna-7B",
+)
+gradio_interface.launch()

requirements.txt

@@ -0,0 +1,68 @@
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+attrs==23.1.0
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+diskcache==5.6.3
+exceptiongroup==1.2.0
+fastapi==0.105.0
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.46.0
+fsspec==2023.12.2
+gradio==4.10.0
+gradio_client==0.7.3
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.25.2
+huggingface-hub==0.19.4
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+llama_cpp_python==0.2.23
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+numpy==1.26.2
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+Pillow==10.1.0
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+tomlkit==0.12.0
+toolz==0.12.0
+tqdm==4.66.1
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2023.3
+urllib3==2.1.0
+uvicorn==0.24.0.post1
+websockets==11.0.3
+zipp==3.17.0