Instructions to use apple/OpenELM-1_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/OpenELM-1_1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="apple/OpenELM-1_1B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("apple/OpenELM-1_1B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use apple/OpenELM-1_1B 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" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/apple/OpenELM-1_1B
- SGLang
How to use apple/OpenELM-1_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 "apple/OpenELM-1_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": "apple/OpenELM-1_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 "apple/OpenELM-1_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": "apple/OpenELM-1_1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use apple/OpenELM-1_1B with Docker Model Runner:
docker model run hf.co/apple/OpenELM-1_1B
Fix For NaN Logits in HuggingFace Distribution of OpenELM
#3
by jasonkrone - opened
- modeling_openelm.py +1 -1
modeling_openelm.py
CHANGED
|
@@ -766,7 +766,7 @@ class OpenELMModel(OpenELMPreTrainedModel):
|
|
| 766 |
)
|
| 767 |
|
| 768 |
# We use the current dtype to avoid any overflows
|
| 769 |
-
min_dtype = torch.finfo(dtype).min
|
| 770 |
causal_mask = (
|
| 771 |
self.causal_mask[None, None, :, :].repeat(batch_size, 1, 1, 1).to(dtype)
|
| 772 |
* min_dtype
|
|
|
|
| 766 |
)
|
| 767 |
|
| 768 |
# We use the current dtype to avoid any overflows
|
| 769 |
+
min_dtype = torch.finfo(dtype).min / 2
|
| 770 |
causal_mask = (
|
| 771 |
self.causal_mask[None, None, :, :].repeat(batch_size, 1, 1, 1).to(dtype)
|
| 772 |
* min_dtype
|