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 4, 2025

Commit

a9f8dec

verified ·

1 Parent(s): b5578db

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +21 -15

README.md CHANGED Viewed

@@ -186,12 +186,15 @@ The training dataset consisted of 119,117 carefully curated entries focused on s
 - Real-world scenarios and practical advice situations
 - Educational Q&A formatted for instruction following
-All training data was filtered and validated to ensure:
-- Medical accuracy and reliability
 - Appropriate tone and sensitivity for SCI community
 - Removal of potentially harmful or dangerous advice
 - Proper medical disclaimers and context
 ### Training Procedure
 The model was trained using a two-phase approach with QLoRA (Quantized Low-Rank Adaptation):
@@ -246,9 +249,11 @@ Training data underwent extensive preprocessing:
 The model was evaluated using:
 - Held-out test set of SCI-related questions (500 samples)
-- Real-world scenarios from SCI community feedback
-- Medical professional review of sample responses
-- Comparative analysis against general-purpose models
 #### Factors
@@ -261,18 +266,18 @@ Evaluation considered multiple factors:
 #### Metrics
-- **Medical accuracy score**: Professional healthcare review (85% accuracy on factual medical content)
-- **Appropriateness rating**: Community feedback (4.2/5.0 average rating)
 - **Response relevance**: SCI-specific context understanding (82% relevance score)
-- **Safety compliance**: Zero harmful medical advice detected in test samples
 - **Response quality**: Perplexity improvements over base model for SCI domain
 ### Results
 **Quantitative Results:**
 - 40% improvement in SCI domain perplexity over base model
-- 85% medical accuracy on factual SCI content (healthcare professional review)
-- 95% safety compliance (no harmful medical advice detected)
 - 82% average relevance score for SCI-specific contexts
 **Qualitative Results:**
@@ -281,10 +286,10 @@ Evaluation considered multiple factors:
 - Consistent inclusion of medical disclaimers
 - Good balance between being helpful and cautious about medical advice
-**Community Feedback:**
-- SCI community members rated responses as more relevant and helpful compared to general models
-- Healthcare professionals noted improved medical terminology usage
-- Consistent appropriate referrals to medical professionals when needed
 ## Environmental Impact
@@ -359,7 +364,8 @@ basiphobe. (2025). *SCI Assistant: A Specialized AI Assistant for Spinal Cord In
 **Primary Author:** basiphobe
 **Model Development:** Individual research project for SCI community support
-**Medical Consultation:** Content reviewed by healthcare professionals familiar with SCI care
 ## Model Card Contact

 - Real-world scenarios and practical advice situations
 - Educational Q&A formatted for instruction following
+All training data was filtered and curated to ensure:
+- Sources from reputable medical organizations and healthcare professionals
+- Content originally created or reviewed by medical professionals in the SCI field
 - Appropriate tone and sensitivity for SCI community
 - Removal of potentially harmful or dangerous advice
 - Proper medical disclaimers and context
+**Note**: While the source materials were created by medical professionals, this model itself has not undergone independent medical validation.
 ### Training Procedure
 The model was trained using a two-phase approach with QLoRA (Quantized Low-Rank Adaptation):
 The model was evaluated using:
 - Held-out test set of SCI-related questions (500 samples)
+- Manual review of response quality and appropriateness
+- Comparative analysis against general-purpose models on SCI topics
+- Assessment of domain-specific knowledge retention
+**Note**: Evaluation was conducted by the model developer, not independent medical professionals.
 #### Factors
 #### Metrics
+- **Medical accuracy score**: Based on consistency with source medical literature (not independently validated)
+- **Appropriateness rating**: Developer assessment of tone and sensitivity (4.2/5.0 subjective rating)
 - **Response relevance**: SCI-specific context understanding (82% relevance score)
+- **Safety compliance**: No obviously harmful medical advice detected in test samples
 - **Response quality**: Perplexity improvements over base model for SCI domain
 ### Results
 **Quantitative Results:**
 - 40% improvement in SCI domain perplexity over base model
+- Responses demonstrate consistency with source medical literature
+- 95% safety compliance (no obviously harmful medical advice detected)
 - 82% average relevance score for SCI-specific contexts
 **Qualitative Results:**
 - Consistent inclusion of medical disclaimers
 - Good balance between being helpful and cautious about medical advice
+**Limitations of Evaluation:**
+- Evaluation conducted by model developer, not independent medical experts
+- No formal clinical validation or testing with SCI patients
+- Results based on consistency with training sources, not independent medical verification
 ## Environmental Impact
 **Primary Author:** basiphobe
 **Model Development:** Individual research project for SCI community support
+**Data Sources:** Curated from medical literature and educational materials created by healthcare professionals
+**Validation Status:** Model has not undergone independent medical professional validation
 ## Model Card Contact