Instructions to use Jumpr/HF_compatibility_testv3-ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jumpr/HF_compatibility_testv3-ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="Jumpr/HF_compatibility_testv3-ForCausalLM", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Jumpr/HF_compatibility_testv3-ForCausalLM", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jumpr/HF_compatibility_testv3-ForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jumpr/HF_compatibility_testv3-ForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jumpr/HF_compatibility_testv3-ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jumpr/HF_compatibility_testv3-ForCausalLM

SGLang

How to use Jumpr/HF_compatibility_testv3-ForCausalLM 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 "Jumpr/HF_compatibility_testv3-ForCausalLM" \
    --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": "Jumpr/HF_compatibility_testv3-ForCausalLM",
		"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 "Jumpr/HF_compatibility_testv3-ForCausalLM" \
        --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": "Jumpr/HF_compatibility_testv3-ForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jumpr/HF_compatibility_testv3-ForCausalLM with Docker Model Runner:
```
docker model run hf.co/Jumpr/HF_compatibility_testv3-ForCausalLM
```

HF_compatibility_testv3-ForCausalLM / modeling_lightningtransformer.py

Jumpr

Upload model

c7d303a verified 8 days ago

Raw

History Blame Contribute Delete

605 Bytes

	from transformers import PreTrainedModel
	from transformers.generation import GenerationMixin

	from .configuration_lightningtransformer import LightningTransformerModelConfig
	from .lightningtransformer import LightningTransformer


	class LightningTransformerModelForCausalLM(PreTrainedModel, GenerationMixin):
	config_class = LightningTransformerModelConfig

	def __init__(self, config):
	super().__init__(config)
	self.model = LightningTransformer(**config.cfg)
	self.use_cache = False
	self.post_init()

	def forward(self, input_ids, **kwargs):
	return self.model.forward(input_ids)