LLM
Collection
Collection of OpenVINO optimized LLMs
•
129 items
•
Updated
•
16
This is open_llama_3b_v2 model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.
Weight compression was performed using nncf.compress_weights
with the following parameters:
For more information on quantization, check the OpenVINO model optimization guide.
The provided OpenVINO™ IR model is compatible with:
pip install optimum[openvino]
from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM
model_id = "OpenVINO/open_llama_3b_v2-int4-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)
inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)
For more examples and possible optimizations, refer to the OpenVINO Large Language Model Inference Guide.
pip install openvino-genai huggingface_hub
import huggingface_hub as hf_hub
model_id = "OpenVINO/open_llama_3b_v2-int4-ov"
model_path = "open_llama_3b_v2-int4-ov"
hf_hub.snapshot_download(model_id, local_dir=model_path)
import openvino_genai as ov_genai
device = "CPU"
pipe = ov_genai.LLMPipeline(model_path, device)
print(pipe.generate("What is OpenVINO?", max_length=200))
## Limitations
Check the original model card for [original model card](https://huggingface.co/openlm-research/open_llama_3b_v2) for limitations.
## Legal information
The original model is distributed under [apache-2.0](https://choosealicense.com/licenses/apache-2.0/) license. More details can be found in [original model card](https://huggingface.co/openlm-research/open_llama_3b_v2).
## Disclaimer
Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.