Instructions to use hoanghai2110/HyperMambaLM-300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hoanghai2110/HyperMambaLM-300M with Transformers:

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

pipe = pipeline("text-generation", model="hoanghai2110/HyperMambaLM-300M", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hoanghai2110/HyperMambaLM-300M", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hoanghai2110/HyperMambaLM-300M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hoanghai2110/HyperMambaLM-300M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hoanghai2110/HyperMambaLM-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hoanghai2110/HyperMambaLM-300M

SGLang

How to use hoanghai2110/HyperMambaLM-300M 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 "hoanghai2110/HyperMambaLM-300M" \
    --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": "hoanghai2110/HyperMambaLM-300M",
		"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 "hoanghai2110/HyperMambaLM-300M" \
        --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": "hoanghai2110/HyperMambaLM-300M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hoanghai2110/HyperMambaLM-300M with Docker Model Runner:
```
docker model run hf.co/hoanghai2110/HyperMambaLM-300M
```

HyperMambaLM-300M / __init__.py

hoanghai2110

Update __init__.py

610fdbc verified 11 months ago

raw

history blame contribute delete

1.12 kB

	"""
	HyperMambaLM - v1.0.0
	Simple language model
	"""

	# Import main model
	from .modeling_hypermamba import (
	HyperMambaConfig,
	HyperMambaLM,
	MetaLearningModule,
	NeuroSymbolicLayer,
	UltraMambaBlock
	)

	# Import utilities
	from .modeling_utils import (
	AdvancedBPETokenizer,
	ModelProfiler,
	FewShotDataLoader,
	VisualizationUtils
	)

	__version__ = "1.0.0"
	__author__ = "Nguyen Hai"

	__all__ = [
	"HyperMambaConfig",
	"HyperMambaLM",
	"MetaLearningModule",
	"NeuroSymbolicLayer",
	"UltraMambaBlock",
	"AdvancedBPETokenizer",
	"ModelProfiler",
	"FewShotDataLoader",
	"VisualizationUtils",
	]

	# Register models
	def register_models():
	try:
	from transformers import AutoConfig, AutoModel, AutoModelForCausalLM

	AutoConfig.register("hypermamba", HyperMambaConfig)
	AutoModel.register(HyperMambaConfig, HyperMambaLM)
	AutoModelForCausalLM.register(HyperMambaConfig, HyperMambaLM)

	print("Models registered successfully!")
	except ImportError:
	print("Transformers library not found")

	register_models()