transformers/docs/source/en/model_doc/granitemoehybrid.md

GraniteMoeHybrid

Overview

The GraniteMoeHybrid model builds on top of GraniteMoeSharedModel and Bamba. Its decoding layers consist of state space layers or MoE attention layers with shared experts. By default, the attention layers do not use positional encoding.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "ibm-granite/granite-4.0-tiny-preview"
tokenizer = AutoTokenizer.from_pretrained(model_path)

# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto")
model.eval()

# change input text as desired
prompt = "Write a code to find the maximum value in a list of numbers."

# tokenize the text
input_tokens = tokenizer(prompt, return_tensors="pt")
# generate output tokens
output = model.generate(**input_tokens, max_new_tokens=100)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# loop over the batch to print, in this example the batch size is 1
for i in output:
    print(i)

This HF implementation is contributed by Sukriti Sharma and Alexander Brooks.

GraniteMoeHybridConfig

autodoc GraniteMoeHybridConfig

GraniteMoeHybridModel

autodoc GraniteMoeHybridModel - forward

GraniteMoeHybridForCausalLM

autodoc GraniteMoeHybridForCausalLM - forward