Downloads · 30 days
5
26% of all-time downloads
vuiseng9_-_ov-gpt2-fp32-no-cache-4bits
RichardErkhov/vuiseng9_-_ov-gpt2-fp32-no-cache-4bits
vuiseng9_-_ov-gpt2-fp32-no-cache-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
19
Public
Parameters
126M
127 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors127 MB · 97%
Parameter types
How the weights are stored.
U884.9M · 68%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
ov-gpt2-fp32-no-cache - bnb 4bits
- Model creator: https://huggingface.co/vuiseng9/
- Original model: https://huggingface.co/vuiseng9/ov-gpt2-fp32-no-cache/
Original model description:
Notes:
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.
# 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)
- Type
- gpt2
- Created
- Oct 6, 2024
- Updated
- Oct 6, 2024