Duplicate from morenolq/galactica-base

Co-authored-by: Moreno La Quatra <morenolq@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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: Galactica Base (1.3B)
+emoji: 📝
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: morenolq/galactica-base
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("facebook/galactica-1.3b")
+model = AutoModelForCausalLM.from_pretrained("facebook/galactica-1.3b")
+text2text_generator = pipeline("text-generation", model=model, tokenizer=tokenizer, num_workers=2)
+
+def predict(text, max_length=64, temperature=0.7, do_sample=True):
+    text = text.strip()
+    out_text = text2text_generator(text, max_length=max_length, 
+                              temperature=temperature, 
+                              do_sample=do_sample,
+                              eos_token_id = tokenizer.eos_token_id,
+                              bos_token_id = tokenizer.bos_token_id,
+                              pad_token_id = tokenizer.pad_token_id,
+                         )[0]['generated_text']
+    out_text = "<p>" + out_text + "</p>"
+    out_text = out_text.replace(text, text + "<b><span style='background-color: #ffffcc;'>")
+    out_text = out_text +  "</span></b>"
+    out_text = out_text.replace("\n", "<br>")
+    return out_text
+
+iface = gr.Interface(
+    fn=predict, 
+    inputs=[
+        gr.inputs.Textbox(lines=5, label="Input Text"),
+        gr.inputs.Slider(minimum=32, maximum=256, default=64, label="Max Length"),
+        gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.7, step=0.1, label="Temperature"),
+        gr.inputs.Checkbox(label="Do Sample"),
+    ],
+    outputs=gr.HTML(),
+    description="Galactica Base Model",
+    examples=[[
+            "The attention mechanism in LLM is",
+            128,
+            0.7,
+            True
+        ], 
+        [
+            "Title: Attention is all you need\n\nAbstract:",
+            128,
+            0.7,
+            True
+        ]
+    ]
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/paperswithcode/galai
+gradio