Text Generation
Transformers
PyTorch
TensorBoard
Chinese
llama
llama2
chinese-llama2
gogpt2-7b
text-generation-inference
Instructions to use golaxy/gogpt2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use golaxy/gogpt2-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="golaxy/gogpt2-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("golaxy/gogpt2-7b") model = AutoModelForCausalLM.from_pretrained("golaxy/gogpt2-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use golaxy/gogpt2-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "golaxy/gogpt2-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "golaxy/gogpt2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/golaxy/gogpt2-7b
- SGLang
How to use golaxy/gogpt2-7b 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 "golaxy/gogpt2-7b" \ --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": "golaxy/gogpt2-7b", "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 "golaxy/gogpt2-7b" \ --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": "golaxy/gogpt2-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use golaxy/gogpt2-7b with Docker Model Runner:
docker model run hf.co/golaxy/gogpt2-7b
Commit ·
b293e90
1
Parent(s): ffeeb15
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,8 @@ tags:
|
|
| 27 |
|
| 28 |
> ICT中英文底座增强大模型:70亿参数、130亿参数
|
| 29 |
|
|
|
|
|
|
|
| 30 |
## step1:训练分词器
|
| 31 |
|
| 32 |
[🐱怎么从零到一训练一个LLM分词器](https://github.com/yanqiangmiffy/how-to-train-tokenizer)
|
|
|
|
| 27 |
|
| 28 |
> ICT中英文底座增强大模型:70亿参数、130亿参数
|
| 29 |
|
| 30 |
+
[GoGPT-Github](https://github.com/yanqiangmiffy/GoGPT)
|
| 31 |
+
|
| 32 |
## step1:训练分词器
|
| 33 |
|
| 34 |
[🐱怎么从零到一训练一个LLM分词器](https://github.com/yanqiangmiffy/how-to-train-tokenizer)
|