Spaces:
Paused
Paused
File size: 2,373 Bytes
2695082 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
import os
import copy
import time
import llama_cpp
from llama_cpp import Llama
from huggingface_hub import hf_hub_download
import uvicorn
from fastapi import FastAPI, Request
llm = Llama(
model_path=hf_hub_download(
repo_id=os.environ.get("REPO_ID", "TheBloke/Llama-2-7b-Chat-GGUF"),
filename=os.environ.get("MODEL_FILE", "llama-2-7b-chat.Q5_0.gguf"),
),
n_ctx=2048,
n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM
)
history = []
system_message = """
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
"""
def generate_text(message, history):
temp = ""
input_prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n "
for interaction in history:
input_prompt = input_prompt + str(interaction[0]) + " [/INST] " + str(interaction[1]) + " </s><s> [INST] "
input_prompt = input_prompt + str(message) + " [/INST] "
output = llm(
input_prompt,
temperature=0.15,
top_p=0.1,
top_k=40,
repeat_penalty=1.1,
max_tokens=1024,
stop=[
"<|prompter|>",
"<|endoftext|>",
"<|endoftext|> \n",
"ASSISTANT:",
"USER:",
"SYSTEM:",
],
)
# for out in output:
# stream = copy.deepcopy(out)
# temp += stream["choices"][0]["text"]
# yield temp
history = ["init", input_prompt]
print(history)
print(output)
return output
app = FastAPI()
@app.post("/api/generate")
async def generate(request: Request):
# Receive the request as JSON
data = await request.json()
# Check if the event is a completed order
if data['message']:
response = generate_text(data['message'], history)
return {"status": "success", "data":response}
else:
# If the event is not what we're looking for, ignore it
return {"status": "ignored"} |