Instructions to use srang992/Qwen-2.5-3B-Instruct-ov-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use srang992/Qwen-2.5-3B-Instruct-ov-INT4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="srang992/Qwen-2.5-3B-Instruct-ov-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("srang992/Qwen-2.5-3B-Instruct-ov-INT4")
model = AutoModelForCausalLM.from_pretrained("srang992/Qwen-2.5-3B-Instruct-ov-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use srang992/Qwen-2.5-3B-Instruct-ov-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "srang992/Qwen-2.5-3B-Instruct-ov-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "srang992/Qwen-2.5-3B-Instruct-ov-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/srang992/Qwen-2.5-3B-Instruct-ov-INT4

SGLang

How to use srang992/Qwen-2.5-3B-Instruct-ov-INT4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "srang992/Qwen-2.5-3B-Instruct-ov-INT4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "srang992/Qwen-2.5-3B-Instruct-ov-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "srang992/Qwen-2.5-3B-Instruct-ov-INT4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "srang992/Qwen-2.5-3B-Instruct-ov-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use srang992/Qwen-2.5-3B-Instruct-ov-INT4 with Docker Model Runner:
```
docker model run hf.co/srang992/Qwen-2.5-3B-Instruct-ov-INT4
```

Qwen-2.5-3B-Instruct-ov-INT4

Model creator: Qwen
Original model: Qwen2.5-3B-Instruct

Description

This is Qwen2.5-3B-Instruct model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

Quantization Parameters

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

mode: int4_sym
ratio: 0.6
group_size: 64

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

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

<|im_start|>system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>
<|im_start|>user
{input}<|im_end|>

Running Model Inference with Optimum Intel

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 = "srang992/Qwen-2.5-3B-Instruct-ov-INT4"
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.

Running Model Inference with OpenVINO GenAI

Install packages required for using OpenVINO GenAI.

pip install openvino-genai huggingface_hub

Download model from HuggingFace Hub

import huggingface_hub as hf_hub

model_id = "srang992/Qwen-2.5-3B-Instruct-ov-INT4"
model_path = "Qwen-2.5-3B-Instruct-ov-INT4"

hf_hub.snapshot_download(model_id, local_dir=model_path)

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))

Downloads last month: 26

Model tree for srang992/Qwen-2.5-3B-Instruct-ov-INT4

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1276)

this model