Instructions to use luciaquirke/2layer-transformer-tinystories with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luciaquirke/2layer-transformer-tinystories with Transformers:

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

pipe = pipeline("text-generation", model="luciaquirke/2layer-transformer-tinystories")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("luciaquirke/2layer-transformer-tinystories", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luciaquirke/2layer-transformer-tinystories with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luciaquirke/2layer-transformer-tinystories"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luciaquirke/2layer-transformer-tinystories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/luciaquirke/2layer-transformer-tinystories

SGLang

How to use luciaquirke/2layer-transformer-tinystories 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 "luciaquirke/2layer-transformer-tinystories" \
    --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": "luciaquirke/2layer-transformer-tinystories",
		"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 "luciaquirke/2layer-transformer-tinystories" \
        --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": "luciaquirke/2layer-transformer-tinystories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use luciaquirke/2layer-transformer-tinystories with Docker Model Runner:
```
docker model run hf.co/luciaquirke/2layer-transformer-tinystories
```

2layer-transformer-tinystories / config.json

luciaquirke

Upload AttnOnlyForCausalLM

35e2cde verified 7 months ago

Raw History Blame Contribute Delete

451 Bytes

	{
	"architectures": [
	"AttnOnlyForCausalLM"
	],
	"attn_pdrop": 0.0,
	"embd_pdrop": 0.0,
	"hidden_size": 768,
	"layer_norm": false,
	"layer_norm_epsilon": 1e-05,
	"max_position_embeddings": 1024,
	"model_type": "attn_only",
	"num_attention_heads": 12,
	"num_hidden_layers": 2,
	"resid_pdrop": 0.0,
	"special_pos_embed": true,
	"torch_dtype": "float32",
	"transformers_version": "4.55.4",
	"use_cache": true,
	"vocab_size": 50257
	}