Instructions to use nikodoz/qwen2.5-7b-instruct-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikodoz/qwen2.5-7b-instruct-int4 with Transformers:

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

pipe = pipeline("text-generation", model="nikodoz/qwen2.5-7b-instruct-int4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nikodoz/qwen2.5-7b-instruct-int4")
model = AutoModelForCausalLM.from_pretrained("nikodoz/qwen2.5-7b-instruct-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 nikodoz/qwen2.5-7b-instruct-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nikodoz/qwen2.5-7b-instruct-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": "nikodoz/qwen2.5-7b-instruct-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nikodoz/qwen2.5-7b-instruct-int4

SGLang

How to use nikodoz/qwen2.5-7b-instruct-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 "nikodoz/qwen2.5-7b-instruct-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": "nikodoz/qwen2.5-7b-instruct-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 "nikodoz/qwen2.5-7b-instruct-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": "nikodoz/qwen2.5-7b-instruct-int4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nikodoz/qwen2.5-7b-instruct-int4 with Docker Model Runner:
```
docker model run hf.co/nikodoz/qwen2.5-7b-instruct-int4
```

🚀 Qwen2.5-7B-Instruct INT4 量化模型

这是基于 Qwen/Qwen2.5-7B-Instruct 的 INT4 量化版本，使用 bitsandbytes 库进行量化。

📊 模型信息

基础模型: Qwen/Qwen2.5-7B-Instruct
量化类型: INT4 (4-bit)
量化方法: BitsAndBytesConfig with NF4
压缩比率: ~3.5x
显存节省: ~75%

⚙️ 量化配置

from transformers import BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_quant_storage=torch.uint8,
)

🚀 使用方法

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

# 量化配置
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_quant_storage=torch.uint8,
)

# 加载模型和分词器
model_name = "nikodoz/qwen2.5-7b-instruct-int4"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    device_map="auto",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True
)

# 推理示例
messages = [
    {"role": "system", "content": "你是一个有用的AI助手。"},
    {"role": "user", "content": "请介绍一下机器学习。"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.7,
        top_p=0.8,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id,
    )

response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

📈 性能对比

指标	原始模型 (FP16)	量化模型 (INT4)	提升
模型大小	~14GB	~4GB	3.5x 压缩
显存使用	~14GB	~4GB	75% 减少
推理速度	基准	略快	~10%
生成质量	100%	~95%	轻微损失

🔧 环境要求

Python >= 3.8
PyTorch >= 2.0.0
transformers >= 4.40.0
bitsandbytes >= 0.43.0
CUDA >= 11.0

💡 注意事项

首次加载时需要进行量化，可能需要几分钟时间
需要支持 bitsandbytes 的 CUDA 环境
量化会带来轻微的精度损失，但显存使用显著减少
适合在资源受限的环境中部署大型语言模型

📄 许可证

本模型基于原始 Qwen2.5 模型，遵循 Apache-2.0 许可证。

🙏 致谢

Qwen团队提供的优秀基础模型
BitsAndBytes 提供的量化技术
Hugging Face 提供的模型托管平台

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

F32

Model tree for nikodoz/qwen2.5-7b-instruct-int4

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(313)

this model