Instructions to use BotHEX/bothex-gpt-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BotHEX/bothex-gpt-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BotHEX/bothex-gpt-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BotHEX/bothex-gpt-2") model = AutoModelForCausalLM.from_pretrained("BotHEX/bothex-gpt-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BotHEX/bothex-gpt-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BotHEX/bothex-gpt-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BotHEX/bothex-gpt-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BotHEX/bothex-gpt-2
- SGLang
How to use BotHEX/bothex-gpt-2 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 "BotHEX/bothex-gpt-2" \ --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": "BotHEX/bothex-gpt-2", "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 "BotHEX/bothex-gpt-2" \ --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": "BotHEX/bothex-gpt-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BotHEX/bothex-gpt-2 with Docker Model Runner:
docker model run hf.co/BotHEX/bothex-gpt-2
BotHEX โ Foundation Language Model
Creator: Hekima Benjamin Yilika Known as: Hebyl
BotHEX is an independently developed language model created from scratch by Hekima Benjamin Yilika (Hebyl).
The original BotHEX foundation model was initialized and trained from scratch. This repository contains a subsequent training version developed from the original BotHEX model.
Creator & Developer
Hekima Benjamin Yilika, widely known as Hebyl, is the creator and developer of BotHEX.
Purpose
BotHEX is designed to serve as a foundational AI technology for future intelligent applications and AI assistants, including Spark.
Model Architecture
- Architecture: GPT-2
- Parameters: Approximately 400 million
- Transformer layers: 24
- Attention heads: 16
- Hidden dimension: 1024
- Context length: 1024
- Vocabulary size: 91,467
- Data type: BF16
Development
BotHEX is independently developed and trained using GPU resources.
The project is maintained and further developed by its creator, Hebyl.
Future Development
BotHEX is intended to power Spark, an AI assistant independently developed by Hebyl.
Creator: Hekima Benjamin Yilika (Hebyl) Foundation Model: BotHEX Future AI Assistant: Spark
- Downloads last month
- 26
Model tree for BotHEX/bothex-gpt-2
Base model
BotHEX/bothex-gpt-1