metadata

license: apache-2.0
language:
  - en

Mistral-7b-Instruct-v0.1-int8-ov

Model creator: Mistral AI
Original model: Mistral-7b-Instruct-v0.1

Description

This is Mistral-7b-Instruct-v0.1 model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF.

Quantization Parameters

Weight compression was performed using nncf.compress_weights with the following parameters:

mode: INT8_ASYM

For more information on quantization, check the OpenVINO model optimization guide

Compatibility

The provided OpenVINO™ IR model is compatible with:

OpenVINO version 2024.1.0 and higher
Optimum Intel 1.16.0 and higher

Running Model Inference

Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install optimum[openvino]

Run model inference:

from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_id = "OpenVINO/mistral-7b-instrcut-v0.1-int8-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)


messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

For more examples and possible optimizations, refer to the OpenVINO Large Language Model Inference Guide.

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under Apache 2.0 license. More details can be found in original model card.