summerstars/summer-LFM

🚀 Quick Start

# Requirements: torch>=2.8.0, triton>=3.4.0, transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "summerstars/summer-LFM"  # Replace with your repo

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True  # Loads custom CompactReservoirFFN
)

# Inference
inputs = tokenizer("Hello, world!", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0]))