Text Generation
Transformers
Safetensors
English
gabgpt
gift-of-gab
small-language-model
trained-from-scratch
byte-level
game-boy-advance
browser
conversational
custom_code
Instructions to use gszauer/ChatGBA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gszauer/ChatGBA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gszauer/ChatGBA", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("gszauer/ChatGBA", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use gszauer/ChatGBA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gszauer/ChatGBA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gszauer/ChatGBA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/gszauer/ChatGBA
- SGLang
How to use gszauer/ChatGBA 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 "gszauer/ChatGBA" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gszauer/ChatGBA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "gszauer/ChatGBA" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gszauer/ChatGBA", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use gszauer/ChatGBA with Docker Model Runner:
docker model run hf.co/gszauer/ChatGBA
Download tokenization_gabgpt.py from gszauer/ChatGBA: direct link, hf CLI and curl.
- Browser
- Download file 1.45 kB
-
https://huggingface.co/gszauer/ChatGBA/resolve/main/tokenization_gabgpt.py
- Command line
-
hf download hf://gszauer/ChatGBA/tokenization_gabgpt.py
-
curl -L -o tokenization_gabgpt.py https://huggingface.co/gszauer/ChatGBA/resolve/main/tokenization_gabgpt.py
1.45 kB
| """The ChatGBA tokenizer: every UTF-8 byte is one token, ids 0 to 255. | |
| There are no special tokens. The chat markers (<|u|>, <|a|>, <|e|>) are plain | |
| text, spelled out byte by byte, exactly as the model was trained. A reply ends | |
| when the model writes <|e|>: pass stop_strings="<|e|>" (and this tokenizer) | |
| to generate. | |
| """ | |
| from transformers import PreTrainedTokenizer | |
| class GabByteTokenizer(PreTrainedTokenizer): | |
| model_input_names = ["input_ids"] | |
| def __init__(self, **kwargs): | |
| kwargs.setdefault("bos_token", None) | |
| kwargs.setdefault("eos_token", None) | |
| kwargs.setdefault("pad_token", None) | |
| kwargs.setdefault("unk_token", None) | |
| super().__init__(**kwargs) | |
| def vocab_size(self): | |
| return 256 | |
| def get_vocab(self): | |
| return {self._convert_id_to_token(i): i for i in range(256)} | |
| def _tokenize(self, text, **kwargs): | |
| return [self._convert_id_to_token(b) for b in text.encode("utf-8")] | |
| def _convert_token_to_id(self, token): | |
| return int(token[3:-1], 16) # "<0x41>" -> 65 | |
| def _convert_id_to_token(self, index): | |
| return f"<0x{index:02X}>" | |
| def convert_tokens_to_string(self, tokens): | |
| return bytes(self._convert_token_to_id(t) for t in tokens).decode("utf-8", errors="replace") | |
| def save_vocabulary(self, save_directory, filename_prefix=None): | |
| return () # nothing to save: the vocabulary is the 256 byte values | |