Upload 5 files

.gitattributes

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

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,12 +1,11 @@
----
-title: Llama3.1 Fn14133.29122024
-emoji: 📈
-colorFrom: yellow
-colorTo: indigo
-sdk: docker
-pinned: false
-license: mit
-short_description: Modelo refinado com a lei 14.133/2021
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Api Llama3.1
+emoji: 📚
+colorFrom: indigo
+colorTo: gray
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,79 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+# Definição do modelo de dados de entrada
+class Question(BaseModel):
+    text: str
+
+# Inicializando o FastAPI
+app = FastAPI()
+
+# Download e configuração do modelo
+model_name_or_path = "FabioSantos/llama3_1_fn"
+model_basename = "unsloth.Q8_0.gguf"
+model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
+print(f"Model path: {model_path}")
+
+# Configuração do modelo com llama_cpp
+lcpp_llm = Llama(
+    model_path=model_path,
+    n_threads=2,
+    n_batch=512,
+    n_gpu_layers=-1,
+    n_ctx=4096,
+)
+
+# Formato de prompt utilizado no fine-tuning
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+def get_response(text: str) -> str:
+    # Formatar o prompt usando o mesmo template utilizado no fine-tuning
+    formatted_prompt = alpaca_prompt.format(
+        "Você é um assistente do serviço de atendimento ao cliente que deve responder as perguntas dos clientes",
+        text,
+        ""
+    )
+    response = lcpp_llm(
+        prompt=formatted_prompt,
+        max_tokens=256,
+        temperature=0.5,
+        top_p=0.95,
+        top_k=50,
+        stop=['### Response:'],  # Usar "### Response:" como token de parada
+        echo=True
+    )
+    response_text = response['choices'][0]['text']
+    
+    # Extrair a resposta após "### Response:"
+    if "### Response:" in response_text:
+        answer = response_text.split("### Response:")[1].strip()
+    else:
+        answer = response_text.strip()
+
+    print(f"Final Answer: {answer}")
+    return answer
+
+
+# Endpoint para receber uma questão e retornar a resposta
+@app.post("/ask")
+def ask_question(question: Question):
+    response = get_response(question.text)
+    return {"response": response}
+
+# Executa a aplicação
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+

requirements.txt

@@ -0,0 +1,10 @@
+fastapi
+uvicorn
+huggingface_hub
+llama-cpp-python
+pydantic
+transformers
+torch==2.0.1+cu117
+torchvision==0.15.2+cu117
+torchaudio==2.0.2+cu117
+-f https://download.pytorch.org/whl/torch_stable.html