This model is inherited directly from gpt2 in HF model hub. Then, GPT2 Openvino IR from OMZ is copied here. The intended usage of this model is for optimum-intel.

bash

# Install Optimum-Intel

from transformers import AutoTokenizer, pipeline, set_seed, AutoModelForCausalLM
from optimum.intel.openvino import OVModelForCausalLM

model_id="vuiseng9/ov-gpt2-fp32-no-cache"
model = OVModelForCausalLM.from_pretrained(model_id, use_cache=False)
tokenizer = AutoTokenizer.from_pretrained(model_id)
generator_pipe = pipeline('text-generation', model=model, tokenizer=tokenizer)
output = generator_pipe("It's a beautiful day ...", max_length=30, num_return_sequences=1)

RichardErkhov/vuiseng9_-_ov-gpt2-fp32-no-cache-8bits

Notes:

RichardErkhov/
vuiseng9_-_ov-gpt2-fp32-no-cache-8bits