README.md

---
license: llama3.2
language:
- en
base_model:
- meta-llama/Llama-3.2-1B-Instruct
pipeline_tag: text-generation
library_name: transformers
---

# Llama-3.2-1B-Instruct-ov-INT8
* Model creator: [Meta Llama](https://huggingface.co/meta-llama)
 * Original model: [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)

## Description
This is [Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT8 by [NNCF](https://github.com/openvinotoolkit/nncf).

## Quantization Parameters

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

* mode: **int8_asym**
* ratio: **1**
* group_size: **128**

For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).


## Compatibility

The provided OpenVINO™ IR model is compatible with:

* OpenVINO version 2024.4.0 and higher
* Optimum Intel 1.19.0 and higher

## Prompt Template

```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a helpful assistant.<|eot_id|>

<|start_header_id|>user<|end_header_id|>

{input}<|eot_id|>
```

## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)


1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:

```
pip install optimum[openvino]
```

2. Run model inference:

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

model_id = "srang992/Llama-3.2-1B-Instruct-ov-INT8"
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](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).

## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)

1. Install packages required for using OpenVINO GenAI.
```
pip install openvino-genai huggingface_hub
```

2. Download model from HuggingFace Hub
   
```
import huggingface_hub as hf_hub

model_id = "srang992/Llama-3.2-1B-Instruct-ov-INT8"
model_path = "Llama-3.2-1B-Instruct-ov-INT8"

hf_hub.snapshot_download(model_id, local_dir=model_path)

```

3. Run model inference:

```
import openvino_genai as ov_genai

device = "CPU"
pipe = ov_genai.LLMPipeline(model_path, device)
print(pipe.generate("What is OpenVINO?", max_length=200))
```