Smilyai-labs/MixSam-exp

SAM1 Hybrid Model

Architecture

• Transformer + CNN + RNN
• Parameters: 253,748,736 (~253.7M)
• 24L × 768d × 12H

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("path/to/model")
model = AutoModelForCausalLM.from_pretrained("path/to/model")

prompt = "User: Hello!\nSam:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))