Downloads · 30 days
59
14% of all-time downloads
OpenVINO/starcoder2-7b-fp16-ov
starcoder2-7b-fp16-ov is a text generation model from OpenVINO. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as bigcode-openrail-m.
Model creator: BigCode Original model: bigcode/starcoder2-7b
Downloads · 30 days
59
14% of all-time downloads
All-time downloads
425
Public
Repo size
14.4 GB
Likes
0
Public
Click a slice to open those files.
.bin14.4 GB · 100%
From the Hugging Face model README
This is bigcode/starcoder2-7b model converted to the OpenVINO™ IR (Intermediate Representation) format.
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/starcoder2-7b-fp16-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)
inputs = tokenizer("def print_hello_world():", 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/starcoder2-7b-fp16-ov"
model_path = "starcoder2-7b-fp16-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("def print_hello_world():", max_length=200))
More GenAI usage examples can be found in OpenVINO GenAI library docs and samples
The original model is distributed under bigcode-openrail-m license. More details can be found in bigcode/starcoder2-7b.
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. 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.