Duplicate from awinml/falcon-7b-instruct-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: Falcon 7b Instruct Api
+emoji: 💻
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.35.2
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: awinml/falcon-7b-instruct-api
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "tiiuae/falcon-7b-instruct",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+    low_cpu_mem_usage=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
+
+
+def generate_text(input_text):
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+    attention_mask = torch.ones(input_ids.shape)
+
+    output = model.generate(
+        input_ids,
+        attention_mask=attention_mask,
+        max_length=200,
+        do_sample=True,
+        top_k=10,
+        num_return_sequences=1,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+
+    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(output_text)
+
+    # Remove Prompt Echo from Generated Text
+    cleaned_output_text = output_text.replace(input_text, "")
+    return cleaned_output_text
+
+
+text_generation_interface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.inputs.Textbox(label="Input Text"),
+    ],
+    outputs=gr.inputs.Textbox(label="Generated Text"),
+    title="Falcon-7B Instruct",
+).launch()

requirements.txt

@@ -0,0 +1,5 @@
+datasets
+transformers
+accelerate
+einops
+safetensors