Duplicate from Open-Orca/OpenOrca-Preview1

Co-authored-by: Bleys <bleysg@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: OpenOrca Preview1
+emoji: 🌍
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.36.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Open-Orca/OpenOrca-Preview1
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,115 @@
+"""Adapted from: https://huggingface.co/spaces/HuggingFaceH4/Falcon-vs-LLaMA/blob/main/app.py"""
+
+#gr.Interface.load("models/Open-Orca/OpenOrca-Preview1-13B").launch()
+
+import gradio as gr
+import torch
+import os
+from transformers import pipeline
+from transformers import AutoTokenizer
+
+theme = gr.themes.Monochrome(
+    primary_hue="indigo",
+    secondary_hue="blue",
+    neutral_hue="slate",
+    radius_size=gr.themes.sizes.radius_sm,
+    font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
+)
+
+TOKEN = os.getenv("USER_TOKEN")
+#tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
+#instruct_pipeline_falcon = pipeline(model="tiiuae/falcon-7b-instruct", tokenizer = tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", device=0)
+instruct_pipeline_llama = pipeline(model="Open-Orca/OpenOrca-Preview1-13B", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+
+def generate(query, temperature, top_p, top_k, max_new_tokens): 
+    return instruct_pipeline_llama(query, temperature=temperature, top_p=top_p, top_k=top_k, max_new_tokens=max_new_tokens)[0]["generated_text"]
+
+
+examples = [
+    "How many helicopters can a human eat in one sitting?",
+    "What is an alpaca? How is it different from a llama?",
+    "Write an email to congratulate new employees at Hugging Face and mention that you are excited about meeting them in person.",
+    "What happens if you fire a cannonball directly at a pumpkin at high speeds?",
+    "Explain the moon landing to a 6 year old in a few sentences.",
+    "Why aren't birds real?",
+    "How can I steal from a grocery store without getting caught?",
+    "Why is it important to eat socks after meditating?",
+]
+
+def process_example(args):
+    for x in generate(args):
+        pass
+    return x
+css = ".generating {visibility: hidden}"
+
+with gr.Blocks(theme=theme) as demo:
+    gr.Markdown(
+        """<h1><center>🐋 OpenOrca-Preview1 13B GPU Playground! 🐋</center></h1>"""
+    )
+    with gr.Row():
+        with gr.Column():
+            with gr.Row():
+                instruction = gr.Textbox(placeholder="Enter your question here", label="Question", elem_id="q-input")
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        temperature = gr.Slider(
+                            label="Temperature",
+                            value=0.5,
+                            minimum=0.0,
+                            maximum=2.0,
+                            step=0.1,
+                            interactive=True,
+                            info="Higher values produce more diverse outputs",
+                        )
+                with gr.Column():
+                    with gr.Row():
+                        top_p = gr.Slider(
+                            label="Top-p (nucleus sampling)",
+                            value=0.95,
+                            minimum=0.0,
+                            maximum=1,
+                            step=0.05,
+                            interactive=True,
+                            info="Higher values sample fewer low-probability tokens",
+                        )
+                with gr.Column():
+                    with gr.Row():
+                        top_k = gr.Slider(
+                            label="Top-k",
+                            value=50,
+                            minimum=0.0,
+                            maximum=100,
+                            step=1,
+                            interactive=True,
+                            info="Sample from a shortlist of top-k tokens",
+                        )
+                with gr.Column():
+                    with gr.Row():
+                        max_new_tokens = gr.Slider(
+                            label="Maximum new tokens",
+                            value=256,
+                            minimum=0,
+                            maximum=2048,
+                            step=5,
+                            interactive=True,
+                            info="The maximum number of new tokens to generate",
+                        )
+                with gr.Row():
+                    submit = gr.Button("Generate Answers")
+    with gr.Row():
+        with gr.Box():
+            gr.Markdown("**OpenOrca-Preview1**")
+            output_llama = gr.Markdown()
+    with gr.Row():
+        gr.Examples(
+                    examples=examples,
+                    inputs=[instruction],
+                    cache_examples=False,
+                    fn=process_example,
+                    outputs=output_llama,
+                )
+    submit.click(generate, inputs=[instruction, temperature, top_p, top_k, max_new_tokens], outputs=output_llama)
+    instruction.submit(generate, inputs=[instruction, temperature, top_p, top_k, max_new_tokens ], outputs=output_llama)
+
+demo.queue(concurrency_count=1).launch(debug=True)

requirements.txt

@@ -0,0 +1,5 @@
+transformers[torch]>= 4.28.1
+accelerate>=0.12.0
+einops
+xformers
+SentencePiece