Duplicate from teknium/Replit-v1-CodeInstruct-3B

Co-authored-by: Teknium <teknium@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 +1,13 @@
+---
+title: Replit V1 CodeInstruct 3B
+emoji: 🏢
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+duplicated_from: teknium/Replit-v1-CodeInstruct-3B
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,75 @@
+import os
+import gradio as gr
+import torch
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+REPO = "teknium/Replit-v1-CodeInstruct-3B"
+
+description = """# <h1 style="text-align: center; color: white;"><span style='color: #F26207;'> Code Generation by Instruction with Replit-v1-CodeInstruct-3B </h1>
+<span style="color: white; text-align: center;"> This model is trained on a large amount of code and fine tuned on code-instruct datasets. You can type an instruction in the ### Instruction: section and received code generation.</span>"""
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tokenizer = AutoTokenizer.from_pretrained(REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(REPO, torch_dtype=torch.bfloat16, trust_remote_code=True)
+model.to(device)
+
+model.eval()
+
+custom_css = """
+.gradio-container {
+    background-color: #0D1525; 
+    color:white
+}
+#orange-button {
+    background: #F26207 !important;
+    color: white;
+}
+.cm-gutters{
+    border: none !important;
+}
+"""
+
+def post_processing(prompt, completion):
+    return prompt + completion
+
+def code_generation(prompt, max_new_tokens=128, temperature=0.2, top_p=0.9, eos_token_id=tokenizer.eos_token_id):
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
+    generated_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, do_sample=True, use_cache=True, temperature=temperature, top_p=top_p, eos_token_id=eos_token_id)
+    completion = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_spaces=False)
+    return post_processing(prompt, completion)
+
+demo = gr.Blocks(
+    css=custom_css
+)
+
+with demo:
+    gr.Markdown(value=description)
+    with gr.Row():
+        input_col , settings_col  = gr.Column(scale=6), gr.Column(scale=6), 
+        with input_col:
+            code = gr.Code(lines=28,label='Input', value="### Instruction:\n\n### Response:")
+        with settings_col:
+            with gr.Accordion("Generation Settings", open=True):
+                max_new_tokens= gr.Slider(
+                    minimum=8,
+                    maximum=128,
+                    step=1,
+                    value=48,
+                    label="Max Tokens",
+                )
+                temperature = gr.Slider(
+                    minimum=0.1,
+                    maximum=2.5,
+                    step=0.1,
+                    value=0.2,
+                    label="Temperature",
+                )
+
+    with gr.Row():
+        run = gr.Button(elem_id="orange-button", value="Generate Response")
+
+    event = run.click(code_generation, [code, max_new_tokens, temperature], code, api_name="predict")
+
+demo.queue(max_size=40).launch()

requirements.txt

@@ -0,0 +1,5 @@
+einops
+sentencepiece
+torch
+transformers
+gradio