Duplicate from mrm8488/santacoder-dockerfiles-completion

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Santacoder Dockefiles completion
+emoji: 🎅🐋
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 3.0.4
+app_file: app.py
+pinned: false
+duplicated_from: mrm8488/santacoder-dockerfiles-completion
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, set_seed, pipeline
+
+title = "SantaCoder 🎅 Dockerfiles 🐋 Completion"
+description = "This is a subspace to make code generation with [SantaCoder fine-tuned on The Stack Dockerfiles](https://huggingface.co/mrm8488/santacoder-finetuned-the-stack-dockerfiles)"
+EXAMPLE_0 = "# Dockerfile for Express API"
+
+
+CKPT = "mrm8488/santacoder-finetuned-the-stack-dockerfiles"
+
+examples = [[EXAMPLE_0, 55, 0.6, 42]]
+tokenizer = AutoTokenizer.from_pretrained(CKPT)
+model = AutoModelForCausalLM.from_pretrained(CKPT, trust_remote_code=True)
+
+
+def code_generation(gen_prompt, max_tokens, temperature=0.6, seed=42):
+    set_seed(seed)
+    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+    generated_text = pipe(gen_prompt, do_sample=True, top_p=0.95, temperature=temperature, max_new_tokens=max_tokens)[0]['generated_text']
+    return generated_text
+
+
+iface = gr.Interface(
+    fn=code_generation, 
+    inputs=[
+        gr.Textbox(lines=10, label="Input code"),
+        gr.inputs.Slider(
+            minimum=8,
+            maximum=256,
+            step=1,
+            default=8,
+            label="Number of tokens to generate",
+        ),
+        gr.inputs.Slider(
+            minimum=0,
+            maximum=2,
+            step=0.1,
+            default=0.6,
+            label="Temperature",
+        ),
+        gr.inputs.Slider(
+            minimum=0,
+            maximum=1000,
+            step=1,
+            default=42,
+            label="Random seed to use for the generation"
+        )
+    ],
+    outputs=gr.Textbox(label="Predicted code", lines=10),
+    examples=examples,
+    layout="horizontal",
+    theme="peach",
+    description=description,
+    title=title
+)
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers==4.19.0
+accelerate==0.10.0
+torch==1.11.0