You can deploy this model and start earning money today!

FlameF0X/
gemma-4-E2B-it-pruned

Name: gemma-4-E2B-it-pruned
Availability: InStock

google/gemma-4-E2B-it

finetune

apache-2.0

endpoints_compatible

Views

No views yet

from transformers import AutoProcessor, AutoModelForCausalLM

MODEL_ID = "FlameF0X/gemma-4-E2B-it-pruned"

# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    dtype="auto",
    device_map="auto"
)
# Prompt
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Write a short joke about saving RAM."},
]

# Process input
text = processor.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True, 
    enable_thinking=False
)
inputs = processor(text=text, return_tensors="pt").to(model.device)
input_len = inputs["input_ids"].shape[-1]

# Generate output
outputs = model.generate(**inputs, max_new_tokens=1024)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)

# Parse output
processor.parse_response(response)