Instructions to use apple/OpenELM-1_1B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apple/OpenELM-1_1B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="apple/OpenELM-1_1B-Instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("apple/OpenELM-1_1B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use apple/OpenELM-1_1B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apple/OpenELM-1_1B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/OpenELM-1_1B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/apple/OpenELM-1_1B-Instruct

SGLang

How to use apple/OpenELM-1_1B-Instruct 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 "apple/OpenELM-1_1B-Instruct" \
    --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": "apple/OpenELM-1_1B-Instruct",
		"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 "apple/OpenELM-1_1B-Instruct" \
        --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": "apple/OpenELM-1_1B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use apple/OpenELM-1_1B-Instruct with Docker Model Runner:
```
docker model run hf.co/apple/OpenELM-1_1B-Instruct
```

OpenELM-1_1B-Instruct / config.json

qicao-apple

add OpenELM-1_1B-Instruct

b418636 about 2 years ago

raw

history blame contribute delete

1.6 kB

	{
	"activation_fn_name": "swish",
	"architectures": [
	"OpenELMForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_openelm.OpenELMConfig",
	"AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
	},
	"bos_token_id": 1,
	"eos_token_id": 2,
	"ffn_dim_divisor": 256,
	"ffn_multipliers": [
	0.5,
	0.63,
	0.76,
	0.89,
	1.02,
	1.15,
	1.28,
	1.41,
	1.54,
	1.67,
	1.8,
	1.93,
	2.06,
	2.19,
	2.31,
	2.44,
	2.57,
	2.7,
	2.83,
	2.96,
	3.09,
	3.22,
	3.35,
	3.48,
	3.61,
	3.74,
	3.87,
	4.0
	],
	"ffn_with_glu": true,
	"head_dim": 64,
	"initializer_range": 0.02,
	"max_context_length": 2048,
	"model_dim": 2048,
	"model_type": "openelm",
	"normalization_layer_name": "rms_norm",
	"normalize_qk_projections": true,
	"num_gqa_groups": 4,
	"num_kv_heads": [
	4,
	4,
	4,
	5,
	5,
	5,
	5,
	5,
	5,
	5,
	6,
	6,
	6,
	6,
	6,
	6,
	6,
	6,
	7,
	7,
	7,
	7,
	7,
	7,
	8,
	8,
	8,
	8
	],
	"num_query_heads": [
	16,
	16,
	16,
	20,
	20,
	20,
	20,
	20,
	20,
	20,
	24,
	24,
	24,
	24,
	24,
	24,
	24,
	24,
	28,
	28,
	28,
	28,
	28,
	28,
	32,
	32,
	32,
	32
	],
	"num_transformer_layers": 28,
	"qkv_multipliers": [
	0.5,
	1.0
	],
	"rope_freq_constant": 10000,
	"rope_max_length": 4096,
	"share_input_output_layers": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.39.3",
	"use_cache": true,
	"vocab_size": 32000
	}