Upload 3 files

DockerFile

@@ -0,0 +1,22 @@
+FROM python:3.10
+
+WORKDIR /code
+
+RUN pip install --no-cache-dir --upgrade pip
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH 
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app/
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,51 @@
+from fastapi import FastAPI, HTTPException, Depends, Request
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import os
+import huggingface_hub
+
+app = FastAPI()
+
+EXPECTED_TOKEN = os.environ.get("EXPECTED_TOKEN")
+REPO_ID = "Day23/coder-personal-use"
+MODEL_FOLDER = "model"
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+model_dir = huggingface_hub.snapshot_download(repo_id=REPO_ID, allow_patterns=["model/*"])
+
+tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_dir,
+    trust_remote_code=True,
+    device_map=device,
+)
+
+@app.post("/generate")
+async def generate_text(request: Request):
+    """Gera um texto com base na entrada fornecida."""
+    
+    data = await request.json()
+    user_message = data.get("message")
+    
+    if not user_message:
+        raise HTTPException(status_code=400, detail="O campo 'message' é obrigatório.")
+    
+    messages = [{'role': 'user', 'content': user_message}]
+    
+    inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(device)
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs,
+            max_new_tokens=512,
+            do_sample=True,
+            top_k=50,
+            top_p=0.95,
+            num_return_sequences=1,
+            eos_token_id=tokenizer.eos_token_id
+        )
+    
+    generated_text = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+    
+    return {"response": generated_text}

requirements.txt

@@ -0,0 +1,82 @@
+absl-py==1.4.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+appdirs==1.4.4
+async-timeout==4.0.3
+attrs==23.1.0
+certifi==2023.7.22
+cffi==1.15.1
+charset-normalizer==3.2.0
+click==8.1.7
+cmake==3.25.0
+colorama==0.4.6
+contourpy==1.1.0
+cycler==0.11.0
+Cython==3.0.2
+dill==0.3.7
+docker-pycreds==0.4.0
+filelock==3.12.3
+fonttools==4.42.1
+frozenlist==1.4.0
+fsspec==2023.6.0
+gensim==4.3.2
+gitdb==4.0.10
+GitPython==3.1.32
+huggingface-hub==0.16.4
+idna==3.4
+Jinja2==3.1.2
+joblib==1.3.2
+kiwisolver==1.4.5
+lit==15.0.7
+lxml==4.9.3
+MarkupSafe==2.1.2
+mpmath==1.2.1
+multidict==6.0.4
+multiprocess==0.70.15
+networkx==3.0
+nltk==3.8.1
+numpy==1.23.5
+packaging==23.1
+pathtools==0.1.2
+Pillow==9.3.0
+portalocker==2.7.0
+protobuf==4.24.2
+psutil==5.9.5
+pyarrow==13.0.0
+pycparser==2.21
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytz==2023.3
+PyYAML==6.0.1
+regex==2023.8.8
+requests==2.31.0
+rouge-score==0.1.2
+sacrebleu==2.3.1
+safetensors==0.3.3
+scikit-learn==1.3.0
+scipy==1.11.2
+sentencepiece==0.1.99
+sentry-sdk==1.30.0
+setproctitle==1.3.2
+six==1.16.0
+smart-open==6.3.0
+smmap==5.0.0
+sympy==1.11.1
+tabulate==0.9.0
+threadpoolctl==3.2.0
+tokenizers==0.13.3
+torch==2.0.1
+torchaudio==2.0.2
+torchvision==0.15.2
+tqdm==4.66.1
+transformers==4.32.1
+triton==2.0.0
+typing_extensions==4.7.1
+tzdata==2023.3
+urllib3==2.0.4
+wandb==0.15.9
+xxhash==3.3.0
+yarl==1.9.2
+uvicorn==0.23.2
+fastapi>=0.100.0
+huggingface_hub>=0.0.19