Instructions to use RichardErkhov/Maykeye_-_TinyLLama-v0-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Maykeye_-_TinyLLama-v0-8bits with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RichardErkhov/Maykeye_-_TinyLLama-v0-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/Maykeye_-_TinyLLama-v0-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/Maykeye_-_TinyLLama-v0-8bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RichardErkhov/Maykeye_-_TinyLLama-v0-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/Maykeye_-_TinyLLama-v0-8bits

SGLang

How to use RichardErkhov/Maykeye_-_TinyLLama-v0-8bits 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 "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits" \
    --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": "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits",
		"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 "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits" \
        --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": "RichardErkhov/Maykeye_-_TinyLLama-v0-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/Maykeye_-_TinyLLama-v0-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Maykeye_-_TinyLLama-v0-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLLama-v0 - bnb 8bits

Model creator: https://huggingface.co/Maykeye/
Original model: https://huggingface.co/Maykeye/TinyLLama-v0/

Original model description:

license: apache-2.0

This is a first version of recreating roneneldan/TinyStories-1M but using Llama architecture.

Full training process is included in the notebook train.ipynb. Recreating it as simple as downloading TinyStoriesV2-GPT4-train.txt and TinyStoriesV2-GPT4-valid.txt in the same folder with the notebook and running the cells. Validation content is not used by the script so you put anythin in
Backup directory has a script do_backup that I used to copy weights from remote machine to local. Weight are generated too quickly, so by the time script copied weihgt N+1
This is extremely PoC version. Training truncates stories that are longer than context size and doesn't use any sliding window to train story not from the start
Training took approximately 9 hours (3 hours per epoch) on 40GB A100. ~30GB VRAM was used
I use tokenizer from open_llama_3b. However I had troubles with it locally(https://github.com/openlm-research/open_llama/issues/69). I had no troubles on the cloud machine with preninstalled libraries.
Demo script is demo.py
Validation script is provided: valid.py. use it like python valid.py path/to/TinyStoriesV2-GPT4-valid.txt [optional-model-id-or-path]: After training I decided that it's not necessary to beat validation into chunks
Also this version uses very stupid caching mechinsm to shuffle stories for training: it keeps cache of N recently loaded chunks so if random shuffle asks for a story, it may use cache or load chunk. Training dataset is too small, so in next versions I will get rid of it.

from transformers import AutoModelForCausalLM, AutoTokenizer

Downloads last month: 2

Safetensors

Model size

4.63M params

Tensor type

F32

F16