Upload 3 files

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,58 @@
+from fastapi import FastAPI, Header, HTTPException
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+app = FastAPI()
+
+# -----------------------------
+# MODEL
+# -----------------------------
+MODEL_NAME = "lfm-research/LFM-2.5-1.2B-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    device_map="auto",
+    torch_dtype=torch.float16
+)
+
+# -----------------------------
+# YOUR CUSTOM API KEY
+# -----------------------------
+API_KEY = "Model12134-1344"
+
+class Prompt(BaseModel):
+    message: str
+
+@app.post("/chat")
+def chat(
+    prompt: Prompt,
+    x_api_key: str = Header(None)
+):
+    # ---- API KEY VALIDATION ----
+    if not x_api_key:
+        raise HTTPException(status_code=401, detail="API key missing")
+
+    if x_api_key != API_KEY:
+        raise HTTPException(status_code=403, detail="Invalid API key")
+
+    inputs = tokenizer(
+        prompt.message,
+        return_tensors="pt"
+    ).to(model.device)
+
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        temperature=0.3,
+        do_sample=True
+    )
+
+    response = tokenizer.decode(
+        outputs[0][inputs["input_ids"].shape[-1]:],
+        skip_special_tokens=True
+    )
+
+    return {"response": response}

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+torch
+transformers
+accelerate
+sentencepiece