Instructions to use Mayuresh231/tiny-transformer-29m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mayuresh231/tiny-transformer-29m with Transformers:

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

pipe = pipeline("text-generation", model="Mayuresh231/tiny-transformer-29m", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Mayuresh231/tiny-transformer-29m", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mayuresh231/tiny-transformer-29m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mayuresh231/tiny-transformer-29m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mayuresh231/tiny-transformer-29m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mayuresh231/tiny-transformer-29m

SGLang

How to use Mayuresh231/tiny-transformer-29m 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 "Mayuresh231/tiny-transformer-29m" \
    --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": "Mayuresh231/tiny-transformer-29m",
		"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 "Mayuresh231/tiny-transformer-29m" \
        --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": "Mayuresh231/tiny-transformer-29m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mayuresh231/tiny-transformer-29m with Docker Model Runner:
```
docker model run hf.co/Mayuresh231/tiny-transformer-29m
```

tiny-transformer-29m / samples /generation_config.json

Mayuresh231

Upload folder using huggingface_hub

4a2ff77 verified about 1 month ago

Raw History Blame Contribute Delete

500 Bytes

	{
	"checkpoint": "artifacts\\tinystories_600k\\checkpoint_best.pt",
	"checkpoint_epoch": 4,
	"prompt": "Once upon a time",
	"count": 5,
	"accepted_seeds": [
	100,
	103,
	104,
	106,
	107
	],
	"rejected_non_ascii_seeds": [
	101,
	102,
	105
	],
	"selection_rule": "first five seeds whose decoded output is ASCII",
	"max_new_tokens": 300,
	"temperature": 0.7,
	"top_k": 50,
	"top_p": 0.9,
	"repetition_penalty": 1.08,
	"no_repeat_ngram": 3
	}