File size: 1,233 Bytes
42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 ab072a7 42eafc1 |
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 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_NAME = "kasterkeqi/Lumo-8B-Fork-Sol-Copilot"
class ModelHandler:
def __init__(self):
"""Initialize the model and tokenizer."""
self.device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Loading model on {self.device}...")
self.tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
self.model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME,
torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
).to(self.device)
print("Model loaded successfully.")
def __call__(self, inputs):
"""Handle inference requests."""
prompt = inputs.get("inputs", "")
if not prompt:
return {"error": "No input provided"}
# Tokenize input
input_tokens = self.tokenizer(prompt, return_tensors="pt").to(self.device)
# Generate output
with torch.no_grad():
output_tokens = self.model.generate(**input_tokens, max_length=200)
# Decode output
response = self.tokenizer.decode(output_tokens[0], skip_special_tokens=True)
return {"response": response}
|