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 source/dot.s from gszauer/ChatGBA: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/gszauer/ChatGBA/resolve/main/source/dot.s
- Command line
-
hf download hf://gszauer/ChatGBA/source/dot.s
-
curl -L -o dot.s https://huggingface.co/gszauer/ChatGBA/resolve/main/source/dot.s
1.36 kB
| @ int32_t dot_offset(const uint8_t* bytes, const int32_t* inputs, int n) | |
| @ | |
| @ The sum of bytes[i] x inputs[i], 16 at a time (n is a multiple of 16), the | |
| @ inner loop of every matrix product. ARM code in the fast internal RAM: | |
| @ - the bytes (weights, int8 + 128) come from cartridge ROM four words per | |
| @ LDM, a sequential burst, much cheaper than four separate loads | |
| @ - each byte is unpacked with one AND (a shifted operand), which is why they | |
| @ are stored offset to 0..255 rather than signed | |
| @ - the byte is MLA's second operand: the ARM7 multiplies faster when that | |
| @ operand is small | |
| @ Registers: r0 bytes, r1 inputs, r2 end of bytes, r3 sum, r4-r7 sixteen | |
| @ bytes, r8-r11 four inputs, r12 the mask 255, lr one unpacked byte. | |
| .iwram, "ax" | |
| 2 | |
| dot_offset | |
| dot_offset: | |
| push {r4-r11, lr} | |
| mov r3, #0 | |
| mov r12, #255 | |
| add r2, r0, r2 | |
| 1: ldmia r0!, {r4-r7} | |
| word, r4, r5, r6, r7 | |
| ldmia r1!, {r8-r11} | |
| and lr, r12, \word | |
| mla r3, r8, lr, r3 | |
| and lr, r12, \word, lsr #8 | |
| mla r3, r9, lr, r3 | |
| and lr, r12, \word, lsr #16 | |
| mla r3, r10, lr, r3 | |
| mov lr, \word, lsr #24 | |
| mla r3, r11, lr, r3 | |
| cmp r0, r2 | |
| blo 1b | |
| mov r0, r3 | |
| pop {r4-r11, lr} | |
| bx lr | |