Text Generation
Transformers
ONNX
Safetensors
English
ijk_byte_gpt
gpt
byte-tokenization
mobile
embedded
custom_code
Instructions to use ijktech/ByteGPT-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ijktech/ByteGPT-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ijktech/ByteGPT-small", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ijktech/ByteGPT-small", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ijktech/ByteGPT-small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ijktech/ByteGPT-small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ijktech/ByteGPT-small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ijktech/ByteGPT-small
- SGLang
How to use ijktech/ByteGPT-small 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 "ijktech/ByteGPT-small" \ --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": "ijktech/ByteGPT-small", "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 "ijktech/ByteGPT-small" \ --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": "ijktech/ByteGPT-small", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ijktech/ByteGPT-small with Docker Model Runner:
docker model run hf.co/ijktech/ByteGPT-small
Add README with project details
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
<h1 align="center">
|
| 2 |
<img src="logo.png" alt="IJK Technology" width="100" style="vertical-align: middle; margin-right: 10px;">
|
| 3 |
IJK Technology – ByteGPT-small
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- gpt
|
| 5 |
+
- byte-tokenization
|
| 6 |
+
- mobile
|
| 7 |
+
- embedded
|
| 8 |
+
license: cc-by-nc-4.0
|
| 9 |
+
datasets:
|
| 10 |
+
- custom
|
| 11 |
+
- web
|
| 12 |
+
language: en
|
| 13 |
+
widget:
|
| 14 |
+
- text: "In order to make pancakes, you need to"
|
| 15 |
+
- text: "Once upon a time"
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
<h1 align="center">
|
| 19 |
<img src="logo.png" alt="IJK Technology" width="100" style="vertical-align: middle; margin-right: 10px;">
|
| 20 |
IJK Technology – ByteGPT-small
|