MythoMax-L2-13b-FP8-dynamic

Gryphe/MythoMax-L2-13b

Quantized version of Gryphe/MythoMax-L2-13b.

Creation

This model was created with llm-compressor by running the code snippet below.

from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model
model_stub = "Gryphe/MythoMax-L2-13b"
model_name = model_stub.split("/")[-1]

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    torch_dtype="auto",
)

tokenizer = AutoTokenizer.from_pretrained(model_stub)

# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=["lm_head"],
)

# Apply quantization
oneshot(
    model=model,
    recipe=recipe,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-FP8-dynamic"
model.generation_config.do_sample = True
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")