Instructions to use VickyK09/neuronerd-llama-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VickyK09/neuronerd-llama-8b with Transformers:

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

pipe = pipeline("text-generation", model="VickyK09/neuronerd-llama-8b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("VickyK09/neuronerd-llama-8b")
model = AutoModelForMultimodalLM.from_pretrained("VickyK09/neuronerd-llama-8b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VickyK09/neuronerd-llama-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VickyK09/neuronerd-llama-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VickyK09/neuronerd-llama-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VickyK09/neuronerd-llama-8b

SGLang

How to use VickyK09/neuronerd-llama-8b 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 "VickyK09/neuronerd-llama-8b" \
    --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": "VickyK09/neuronerd-llama-8b",
		"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 "VickyK09/neuronerd-llama-8b" \
        --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": "VickyK09/neuronerd-llama-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use VickyK09/neuronerd-llama-8b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VickyK09/neuronerd-llama-8b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VickyK09/neuronerd-llama-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VickyK09/neuronerd-llama-8b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="VickyK09/neuronerd-llama-8b",
    max_seq_length=2048,
)

Docker Model Runner
How to use VickyK09/neuronerd-llama-8b with Docker Model Runner:
```
docker model run hf.co/VickyK09/neuronerd-llama-8b
```

🧠 NeuroNerd - Llama 3.1 8B

A fine-tuned Llama 3.1 8B model specialized in neuroscience and cognitive science. Trained on curated Q&A pairs extracted from graduate-level neuroscience textbooks.

Model Description

NeuroNerd is designed to answer questions about:

🔬 Cognitive Neuroscience
🧬 Computational Neuroscience
🧪 Foundations of Neuroscience
🎓 Graduate-level neuroscience concepts

Training Details

Parameter	Value
Base Model	Llama 3.1 8B
Training Method	QLoRA (4-bit)
LoRA Rank	64
Training Data	8,200+ Q&A pairs
Epochs	~2
Hardware	NVIDIA A100
Framework	Unsloth + HuggingFace TRL

Training Data Sources

The model was trained on Q&A pairs generated from:

Computational Exploration in Cognitive Neuroscience
Foundations of Neuroscience
The Cognitive Neurosciences (Gazzaniga)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("VickyK09/neuronerd-llama-8b")
tokenizer = AutoTokenizer.from_pretrained("VickyK09/neuronerd-llama-8b")

# Format your prompt
prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
What is the role of dopamine in reward learning?

### Response:
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Example Q&A

Q: How do mirror neurons contribute to action understanding?

Mirror neurons fire both when an individual performs an action and when they observe someone else performing the same action. This dual activation pattern suggests they play a crucial role in understanding others' actions by internally simulating observed movements...

Limitations

Specialized for neuroscience; may not perform well on general topics
Based on textbook knowledge up to training data cutoff
Should not be used for medical diagnosis or treatment decisions

License

This model is released under the Llama 3.1 Community License.

Citation

@misc{neuronerd2024,
  author = {VickyK09},
  title = {NeuroNerd: A Fine-tuned Llama 3.1 8B for Neuroscience},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/VickyK09/neuronerd-llama-8b}
}

Built with ❤️ using Unsloth

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for VickyK09/neuronerd-llama-8b

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1410)

this model