Instructions to use explosion-testing/falcon-no-parallel-attn-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use explosion-testing/falcon-no-parallel-attn-test with Transformers:

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

pipe = pipeline("text-generation", model="explosion-testing/falcon-no-parallel-attn-test", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("explosion-testing/falcon-no-parallel-attn-test", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use explosion-testing/falcon-no-parallel-attn-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "explosion-testing/falcon-no-parallel-attn-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "explosion-testing/falcon-no-parallel-attn-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/explosion-testing/falcon-no-parallel-attn-test

SGLang

How to use explosion-testing/falcon-no-parallel-attn-test 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 "explosion-testing/falcon-no-parallel-attn-test" \
    --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": "explosion-testing/falcon-no-parallel-attn-test",
		"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 "explosion-testing/falcon-no-parallel-attn-test" \
        --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": "explosion-testing/falcon-no-parallel-attn-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use explosion-testing/falcon-no-parallel-attn-test with Docker Model Runner:
```
docker model run hf.co/explosion-testing/falcon-no-parallel-attn-test
```

falcon-no-parallel-attn-test

Commit History

Adding `safetensors` variant of this model

9364b01
verified

SFconvertbot commited on May 20, 2025

Fix loading from HF transformers

f9122de

Daniël de Kok commited on Jul 14, 2023

Fixup settings

54e8cc9

Daniël de Kok commited on Jul 14, 2023

Test model for Falcon without parallel attention

7ea1ac6

Daniël de Kok commited on Jul 14, 2023

initial commit

06184ec

Daniël de Kok commited on Jul 14, 2023

Commit History

Adding `safetensors` variant of this model 9364b01 verified

Fix loading from HF transformers f9122de

Fixup settings 54e8cc9

Test model for Falcon without parallel attention 7ea1ac6

initial commit 06184ec

Adding `safetensors` variant of this model

9364b01
verified

Fix loading from HF transformers

f9122de

Fixup settings

54e8cc9

Test model for Falcon without parallel attention

7ea1ac6

initial commit

06184ec