Spaces:
Runtime error
Runtime error
File size: 1,445 Bytes
0314811 37527e9 0314811 97f6c69 37527e9 65b6e4c f726f33 b46d5c6 65b6e4c daf036c 3d2a79c daf036c b46d5c6 daf036c 97f6c69 79d370e 97f6c69 65b6e4c 97f6c69 0314811 bf5c4b9 97f6c69 bf5c4b9 65b6e4c 0314811 84927e5 |
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 |
from fastapi import FastAPI, HTTPException
from transformers import AutoModelForCausalLM, AutoTokenizer
import os
import copy
import time
import llama_cpp
from llama_cpp import Llama
from huggingface_hub import hf_hub_download
import transformers
import torch
app = FastAPI()
"""
model_path = hf_hub_download(
repo_id="TheBloke/Mistral-7B-v0.1-GGUF",
filename="mistral-7b-v0.1.Q4_K_M.gguf")
llm = Llama(
model_path=model_path,
n_ctx=2048,
n_threads=2
)
"""
@app.get("/")
async def generate_text():
try:
"""
output = llm(
"Q: Name the planets in the solar system? A: ",
max_tokens=32,
stop=["Q:", "\n"],
echo=True)
output = llm.create_chat_completion(
messages=[
{
"role": "system",
"content": "You are a helpful assistant that outputs in JSON.",
},
{"role": "user", "content": "Who won the world series in 2020"},
],
response_format={
"type": "json_object",
},
temperature=0.7,
)
"""
model_id = "meta-llama/Meta-Llama-3-8B"
pipeline = transformers.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto")
pipeline("Hey how are you doing today?")
return pipeline("Hey how are you doing today?")
except Exception as e:
raise HTTPException(status_code=500, detail=str(e)) |