Instructions to use HomeBrewedLabs/metallum-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HomeBrewedLabs/metallum-1b with Transformers:

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

pipe = pipeline("text-generation", model="HomeBrewedLabs/metallum-1b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HomeBrewedLabs/metallum-1b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HomeBrewedLabs/metallum-1b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HomeBrewedLabs/metallum-1b

SGLang

How to use HomeBrewedLabs/metallum-1b 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 "HomeBrewedLabs/metallum-1b" \
    --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": "HomeBrewedLabs/metallum-1b",
		"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 "HomeBrewedLabs/metallum-1b" \
        --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": "HomeBrewedLabs/metallum-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HomeBrewedLabs/metallum-1b with Docker Model Runner:
```
docker model run hf.co/HomeBrewedLabs/metallum-1b
```

metallum-1b / config.json

HomeBrewedLabs

Upload folder using huggingface_hub

f73da3f verified about 1 month ago

Raw

History Blame Contribute Delete

778 Bytes

	{
	"architectures": [
	"MetaLLMForCausalLM"
	],
	"attn_impl": "auto",
	"auto_map": {
	"AutoConfig": "configuration_metallm.MetaLLMConfig",
	"AutoModelForCausalLM": "modeling_metallm.MetaLLMForCausalLM"
	},
	"bos_id": 1,
	"bos_token_id": 1,
	"d_ff": 4864,
	"d_model": 1792,
	"doc_mask": true,
	"hidden_size": 1792,
	"max_position_embeddings": 2048,
	"max_seq_len": 2048,
	"model_type": "metallm",
	"n_heads": 28,
	"n_kv_heads": 14,
	"n_layers": 26,
	"nope_every": 4,
	"norm_eps": 1e-05,
	"num_attention_heads": 28,
	"num_hidden_layers": 26,
	"num_key_value_heads": 14,
	"qk_norm": true,
	"rope_fp32": true,
	"rope_theta": 500000.0,
	"tie_embeddings": true,
	"transformers_version": "4.45.0",
	"vocab_size": 40000,
	"z_loss_weight": 0.0001
	}