Duplicate from awinml/vicuna-7b-ggml-api

Co-authored-by: Ashwin Mathur <awinml@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,14 @@
+---
+title: Vicuna 7b Ggml Api
+emoji: 💻
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.35.2
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: awinml/vicuna-7b-ggml-api
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,60 @@
+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"
+
+examples = [
+    ["What is the capital of France?", "The capital of France is Paris."],
+    [
+        "Who wrote the novel 'Pride and Prejudice'?",
+        "The novel 'Pride and Prejudice' was written by Jane Austen.",
+    ],
+    ["What is the square root of 64?", "The square root of 64 is 8."],
+]
+
+gradio_interface = gr.Interface(
+    fn=generate_text,
+    inputs="text",
+    outputs="text",
+    examples=examples,
+    title="Vicuna-7B",
+)
+gradio_interface.launch()

requirements.txt

@@ -0,0 +1 @@
+llama-cpp-python==0.1.62