Instructions to use golaxy/gogpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use golaxy/gogpt-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="golaxy/gogpt-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("golaxy/gogpt-7b") model = AutoModelForCausalLM.from_pretrained("golaxy/gogpt-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use golaxy/gogpt-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "golaxy/gogpt-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/gogpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/golaxy/gogpt-7b
- SGLang
How to use golaxy/gogpt-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/gogpt-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/gogpt-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/gogpt-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/gogpt-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use golaxy/gogpt-7b with Docker Model Runner:
docker model run hf.co/golaxy/gogpt-7b
Commit ·
7eb70c0
1
Parent(s): 773ca5f
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,7 @@ language:
|
|
| 9 |
tags:
|
| 10 |
- gogpt-7b
|
| 11 |
---
|
|
|
|
| 12 |
# GoGPT
|
| 13 |
|
| 14 |
> GoGPT:ICT中英文底座增强大模型,基于Llama/Llama 2训练的底座大模型,参数规模包括70亿参数、130亿参数
|
|
@@ -28,10 +29,10 @@ tags:
|
|
| 28 |
|
| 29 |
🤗Huggingface上提供了GoGPT权重,目前开放了gogpt-7b和gogpt2-7b权重
|
| 30 |
|
| 31 |
-
| 模型名称
|
| 32 |
-
|------------------------------------------------------------|-----------|------|-------------------------------------------------|
|
| 33 |
-
| [golaxy/gogpt-7b](https://huggingface.co/golaxy/gogpt-7b)
|
| 34 |
-
| [golaxy/
|
| 35 |
|
| 36 |
## 训练细节
|
| 37 |
|
|
|
|
| 9 |
tags:
|
| 10 |
- gogpt-7b
|
| 11 |
---
|
| 12 |
+
|
| 13 |
# GoGPT
|
| 14 |
|
| 15 |
> GoGPT:ICT中英文底座增强大模型,基于Llama/Llama 2训练的底座大模型,参数规模包括70亿参数、130亿参数
|
|
|
|
| 29 |
|
| 30 |
🤗Huggingface上提供了GoGPT权重,目前开放了gogpt-7b和gogpt2-7b权重
|
| 31 |
|
| 32 |
+
| 模型名称 | 基座模型 | 模型大小 | 下载地址 |
|
| 33 |
+
|-------------------------------------------------------------|-----------|------|-------------------------------------------------|
|
| 34 |
+
| [golaxy/gogpt-7b](https://huggingface.co/golaxy/gogpt-7b) | Llama-7b | 7B | [模型下载](https://huggingface.co/golaxy/gogpt-7b) |
|
| 35 |
+
| [golaxy/gogpt2-7b](https://huggingface.co/golaxy/gogpt2-7b) | Llama2-7b | 7B | [模型下载](https://huggingface.co/golaxy/gogpt2-7b) |
|
| 36 |
|
| 37 |
## 训练细节
|
| 38 |
|