Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+zephyr-7b-beta.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY ./zephyr-7b-beta.Q4_K_S.gguf /code/zephyr-7b-beta.Q4_K_S.gguf
+COPY ./main.py /code/main.py
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,8 +1,8 @@
 ---
 title: LLM Deployment Zerocost Api
-emoji: 📈
-colorFrom: pink
-colorTo: gray
+emoji: 😻
+colorFrom: purple
+colorTo: pink
 sdk: docker
 pinned: false
 license: mit

main.py

@@ -0,0 +1,27 @@
+from ctransformers import AutoModelForCausalLM
+from fastapi import FastAPI, Form
+from pydantic import BaseModel
+
+#Model loading
+llm = AutoModelForCausalLM.from_pretrained("zephyr-7b-beta.Q4_K_S.gguf",
+model_type='mistral',
+max_new_tokens = 1096,
+threads = 3,
+)
+   
+
+#Pydantic object
+class validation(BaseModel):
+    prompt: str
+    
+#Fast API
+app = FastAPI()
+
+#Zephyr completion
+@app.post("/llm_on_cpu")
+async def stream(item: validation):
+    system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
+    E_INST = "</s>"
+    user, assistant = "<|user|>", "<|assistant|>"
+    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt.strip()}{E_INST}\n{assistant}\n"
+    return llm(prompt)

requirements.txt

@@ -0,0 +1,6 @@
+python-multipart
+fastapi
+pydantic
+uvicorn
+requests
+ctransformers

zephyr-7b-beta.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafa0b85b2efc15ca33023f3b87f8d0c44ddcace16b3fb608280e0eb8f425cb1
+size 4140373696