Instructions to use Maxtimer97/Llama2SWA256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Maxtimer97/Llama2SWA256 with Transformers:

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

pipe = pipeline("text-generation", model="Maxtimer97/Llama2SWA256", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Maxtimer97/Llama2SWA256", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Maxtimer97/Llama2SWA256 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Maxtimer97/Llama2SWA256"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxtimer97/Llama2SWA256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Maxtimer97/Llama2SWA256

SGLang

How to use Maxtimer97/Llama2SWA256 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 "Maxtimer97/Llama2SWA256" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxtimer97/Llama2SWA256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Maxtimer97/Llama2SWA256" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Maxtimer97/Llama2SWA256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Maxtimer97/Llama2SWA256 with Docker Model Runner:
```
docker model run hf.co/Maxtimer97/Llama2SWA256
```

Maxtimer97 commited on Jul 2, 2025

Commit

e817d17

verified ·

1 Parent(s): e2967d0

Generalized config import

Browse files

Files changed (1) hide show

modeling_hymba.py +4 -2

modeling_hymba.py CHANGED Viewed

@@ -39,8 +39,10 @@ from transformers.utils import (
 from transformers.utils.import_utils import is_torch_fx_available
-from configuration_hymba import HymbaConfig
-# from .configuration_hymba import HymbaConfig
 from torch.utils.checkpoint import checkpoint

 from transformers.utils.import_utils import is_torch_fx_available
+try:
+    from configuration_hymba import HymbaConfig  # Absolute import
+except ImportError:
+    from .configuration_hymba import HymbaConfig
 from torch.utils.checkpoint import checkpoint