Instructions to use melephant/1-layer-addition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use melephant/1-layer-addition with Transformers:

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

pipe = pipeline("text-generation", model="melephant/1-layer-addition", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("melephant/1-layer-addition", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use melephant/1-layer-addition with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "melephant/1-layer-addition"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "melephant/1-layer-addition",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/melephant/1-layer-addition

SGLang

How to use melephant/1-layer-addition 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 "melephant/1-layer-addition" \
    --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": "melephant/1-layer-addition",
		"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 "melephant/1-layer-addition" \
        --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": "melephant/1-layer-addition",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use melephant/1-layer-addition with Docker Model Runner:
```
docker model run hf.co/melephant/1-layer-addition
```

1-layer-addition / config.json

melephant

Publish addition-transformer run s85nnxtf

58223a8 verified 17 days ago

Raw

History Blame Contribute Delete

1.1 kB

	{
	"answer_digits": 5,
	"architecture_version": 2,
	"architectures": [
	"AdditionForCausalLM"
	],
	"attention_logit_divisor": "d_head",
	"attention_output_scale": 0.3333333333333333,
	"auto_map": {
	"AutoConfig": "configuration_addition.AdditionConfig",
	"AutoModelForCausalLM": "modeling_addition.AdditionForCausalLM"
	},
	"base": 10,
	"bias": false,
	"bos_token_id": 0,
	"d_mlp": 128,
	"d_model": 64,
	"digit_token_offset": 3,
	"dtype": "float32",
	"eos_token_id": null,
	"equals_token_id": 2,
	"export_format_version": 2,
	"hidden_size": 64,
	"init_mode": "normal",
	"intermediate_size": 128,
	"is_decoder": true,
	"max_position_embeddings": 16,
	"max_seq_len": 16,
	"model_type": "fixed-width-addition",
	"n_heads": 4,
	"n_layers": 1,
	"normalization": "none",
	"num_attention_heads": 4,
	"num_hidden_layers": 1,
	"operand_digits": 4,
	"pad_token_id": null,
	"plus_token_id": 1,
	"residual_alpha": 0.5,
	"tie_word_embeddings": false,
	"transformers_version": "5.15.0",
	"use_cache": false,
	"vocab_size": 13
	}