intial commit

.gitattributes

@@ -1,35 +0,0 @@
-*.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

@@ -1,12 +0,0 @@
----
-title: Llama7bserver
-emoji: 📈
-colorFrom: pink
-colorTo: yellow
-sdk: gradio
-sdk_version: 5.35.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,30 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+
+# Load model and tokenizer once on startup
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5p-220m")
+model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/codet5p-220m")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = model.to(device)
+
+app = FastAPI()
+
+class Input(BaseModel):
+    prompt: str
+
+@app.post("/generate")
+async def generate(input: Input):
+    inputs = tokenizer(input.prompt, return_tensors="pt").to(device)
+    outputs = model.generate(
+        **inputs,
+        max_length=2048,
+        num_beams=3,
+        early_stopping=True,
+        no_repeat_ngram_size=3,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"output": output_text}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn[standard]
+transformers
+torch

start.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+uvicorn app:app --host 0.0.0.0 --port 7860