Instructions to use GMagoLi/test-upload with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GMagoLi/test-upload with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GMagoLi/test-upload")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GMagoLi/test-upload", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GMagoLi/test-upload with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GMagoLi/test-upload" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GMagoLi/test-upload", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GMagoLi/test-upload
- SGLang
How to use GMagoLi/test-upload 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 "GMagoLi/test-upload" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GMagoLi/test-upload", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "GMagoLi/test-upload" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GMagoLi/test-upload", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GMagoLi/test-upload with Docker Model Runner:
docker model run hf.co/GMagoLi/test-upload
GMagoLi/test-upload
这是一个基于Qwen架构的语言模型,使用VERL框架进行SFT训练。
模型描述
- 模型类型: 因果语言模型
- 架构: Qwen-32B
- 训练框架: VERL FSDP SFT Trainer
- 语言: 中文、英文
- 许可证: Apache 2.0
使用方法
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# 加载模型和tokenizer
model = AutoModelForCausalLM.from_pretrained(
"GMagoLi/test-upload",
trust_remote_code=True,
torch_dtype=torch.bfloat16,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GMagoLi/test-upload", trust_remote_code=True)
# 推理示例
prompt = "你好,请介绍一下你自己。"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(
**inputs,
max_length=512,
temperature=0.7,
do_sample=True,
pad_token_id=tokenizer.eos_token_id
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
训练信息
- 训练步数: 2800 steps
- 批大小: 128
- 学习率调度: Cosine with warmup
- 混合精度: bfloat16
- 数据集: RepoCoder训练数据集v2.3
模型性能
该模型在代码生成和对话任务上表现出色,特别适合:
- 代码生成和补全
- 技术问答
- 多轮对话
注意事项
- 模型较大(32B参数),建议使用GPU推理
- 需要足够的显存(建议24GB+)
- 支持量化推理以降低显存需求
引用
如果使用了本模型,请考虑引用:
@misc{qwen-repocoder-sft,
title={Qwen RepoCoder SFT Model},
author={Your Name},
year={2025},
howpublished={\url{https://huggingface.co/GMagoLi/test-upload}}
}
docker model run hf.co/GMagoLi/test-upload