Instructions to use basiphobe/sci-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basiphobe/sci-assistant with Transformers:

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

pipe = pipeline("text-generation", model="basiphobe/sci-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("basiphobe/sci-assistant")
model = AutoModelForCausalLM.from_pretrained("basiphobe/sci-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use basiphobe/sci-assistant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/basiphobe/sci-assistant

SGLang

How to use basiphobe/sci-assistant 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 "basiphobe/sci-assistant" \
    --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": "basiphobe/sci-assistant",
		"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 "basiphobe/sci-assistant" \
        --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": "basiphobe/sci-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use basiphobe/sci-assistant with Docker Model Runner:
```
docker model run hf.co/basiphobe/sci-assistant
```

basiphobe commited on Aug 5, 2025

Commit

ec774f2

verified ·

1 Parent(s): f2424ac

Add YAML metadata to model card

Browse files

Files changed (1) hide show

README.md +28 -0

README.md CHANGED Viewed

@@ -1,3 +1,31 @@
 # SCI Assistant 7B
 A specialized language model for spinal cord injury (SCI) information and support, based on OpenHermes-2.5-Mistral-7B with custom LoRA fine-tuning.

+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- medical
+- spinal-cord-injury
+- healthcare
+- disability
+- accessibility
+- fine-tuned
+- lora
+- mistral
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+pipeline_tag: text-generation
+widget:
+- text: "What is autonomic dysreflexia?"
+  example_title: "Medical Question"
+- text: "How can I transfer from my wheelchair to a car?"
+  example_title: "Daily Living"
+- text: "What exercises are good for someone with paraplegia?"
+  example_title: "Exercise & Rehabilitation"
+model-index:
+- name: sci-assistant
+  results: []
+---
 # SCI Assistant 7B
 A specialized language model for spinal cord injury (SCI) information and support, based on OpenHermes-2.5-Mistral-7B with custom LoRA fine-tuning.