Instructions to use a8nova/OpenELM-270M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use a8nova/OpenELM-270M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="a8nova/OpenELM-270M-Instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("a8nova/OpenELM-270M-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use a8nova/OpenELM-270M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "a8nova/OpenELM-270M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "a8nova/OpenELM-270M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/a8nova/OpenELM-270M-Instruct

SGLang

How to use a8nova/OpenELM-270M-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 "a8nova/OpenELM-270M-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": "a8nova/OpenELM-270M-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 "a8nova/OpenELM-270M-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": "a8nova/OpenELM-270M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use a8nova/OpenELM-270M-Instruct with Docker Model Runner:
```
docker model run hf.co/a8nova/OpenELM-270M-Instruct
```

a8nova commited on May 19, 2024

Commit

2c39b54

verified ·

1 Parent(s): 35f1c60

Update modeling_openelm.py

Browse files

Files changed (1) hide show

modeling_openelm.py +5 -3

modeling_openelm.py CHANGED Viewed

@@ -778,9 +778,11 @@ class OpenELMModel(OpenELMPreTrainedModel):
             padding_mask = causal_mask[..., :mask_length].eq(0.0) * attention_mask[
                 :, None, None, :
             ].eq(0.0)
-            causal_mask[..., :mask_length] = causal_mask[..., :mask_length].masked_fill(
-                padding_mask, min_dtype
-            )
         if self.config._attn_implementation == "sdpa" and attention_mask is not None:
             # For dynamo, rather use a check on fullgraph=True once this is possible (https://github.com/pytorch/pytorch/pull/120400).

             padding_mask = causal_mask[..., :mask_length].eq(0.0) * attention_mask[
                 :, None, None, :
             ].eq(0.0)
+            causal_mask = causal_mask.clone()
+            causal_mask[..., :mask_length] = causal_mask[..., :mask_length].masked_fill(...)
+            #causal_mask[..., :mask_length] = causal_mask[..., :mask_length].masked_fill(
+            #    padding_mask, min_dtype
+            #)
         if self.config._attn_implementation == "sdpa" and attention_mask is not None:
             # For dynamo, rather use a check on fullgraph=True once this is possible (https://github.com/pytorch/pytorch/pull/120400).