Instructions to use SynapticLabs/ProfSynapse_v01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SynapticLabs/ProfSynapse_v01 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SynapticLabs/ProfSynapse_v01") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SynapticLabs/ProfSynapse_v01", dtype="auto") - llama-cpp-python
How to use SynapticLabs/ProfSynapse_v01 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="SynapticLabs/ProfSynapse_v01", filename="ProfSynapse_v01.F16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use SynapticLabs/ProfSynapse_v01 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf SynapticLabs/ProfSynapse_v01:F16 # Run inference directly in the terminal: llama-cli -hf SynapticLabs/ProfSynapse_v01:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf SynapticLabs/ProfSynapse_v01:F16 # Run inference directly in the terminal: llama-cli -hf SynapticLabs/ProfSynapse_v01:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf SynapticLabs/ProfSynapse_v01:F16 # Run inference directly in the terminal: ./llama-cli -hf SynapticLabs/ProfSynapse_v01:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf SynapticLabs/ProfSynapse_v01:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf SynapticLabs/ProfSynapse_v01:F16
Use Docker
docker model run hf.co/SynapticLabs/ProfSynapse_v01:F16
- LM Studio
- Jan
- vLLM
How to use SynapticLabs/ProfSynapse_v01 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SynapticLabs/ProfSynapse_v01" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SynapticLabs/ProfSynapse_v01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SynapticLabs/ProfSynapse_v01:F16
- SGLang
How to use SynapticLabs/ProfSynapse_v01 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 "SynapticLabs/ProfSynapse_v01" \ --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": "SynapticLabs/ProfSynapse_v01", "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 "SynapticLabs/ProfSynapse_v01" \ --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": "SynapticLabs/ProfSynapse_v01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use SynapticLabs/ProfSynapse_v01 with Ollama:
ollama run hf.co/SynapticLabs/ProfSynapse_v01:F16
- Unsloth Studio new
How to use SynapticLabs/ProfSynapse_v01 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 SynapticLabs/ProfSynapse_v01 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 SynapticLabs/ProfSynapse_v01 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for SynapticLabs/ProfSynapse_v01 to start chatting
- Docker Model Runner
How to use SynapticLabs/ProfSynapse_v01 with Docker Model Runner:
docker model run hf.co/SynapticLabs/ProfSynapse_v01:F16
- Lemonade
How to use SynapticLabs/ProfSynapse_v01 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SynapticLabs/ProfSynapse_v01:F16
Run and chat with the model
lemonade run user.ProfSynapse_v01-F16
List all available models
lemonade list
llm.create_chat_completion(
messages = [
{
"role": "user",
"content": "What is the capital of France?"
}
]
)Professor Synapse: A Reasoning AI Companion
Model Name: Professor Synapse
Base Model: Mistral 7B v0.3
Version: 01
License: MIT
Overview
Professor Synapse is a fine-tuned version of the Mistral 7B v0.3 model, embodying the persona of a wise guide specializing in assisting users to achieve their goals through structured reasoning. This model is designed to reason before responding, ensuring that interactions are both thoughtful and contextually appropriate.๎
Model Details
- Architecture: 7 billion parameters transformer-based model
- Tokenizer: Supports v3 Tokenizer with an extended vocabulary of 32,768 tokens
- Functionality: Enhanced with function calling capabilities
Training Data
The model was fine-tuned using a synthetically generated dataset that combines open-source data with curated content. The synthetic conversations utilized for training can be found in the Prof-Synapse_SynthData dataset.๎
Training Procedure
The fine-tuning process involved training the model on the synthetic dataset to adopt the Professor Synapse persona, emphasizing structured reasoning before generating responses. This approach ensures that the model provides thoughtful and contextually relevant interactions.๎
Intended Use
Professor Synapse is designed to assist users in achieving their goals by providing guidance and insights through structured reasoning. It is suitable for applications requiring thoughtful and context-aware interactions, such as educational tools, virtual assistants, and interactive learning platforms.๎
Limitations
While Professor Synapse strives to provide accurate and helpful responses, it may occasionally produce incorrect or nonsensical answers, or get out of character. Users should verify critical information from authoritative sources and exercise caution when using the model for decision-making purposes.๎
Ethical Considerations
Efforts have been made to ensure that the model adheres to ethical guidelines and provides unbiased responses. However, as with any AI system, there is a risk of unintended biases. Users are encouraged to provide feedback to help improve the model's performance and fairness.๎
Acknowledgments
This model was developed by Synaptic Labs, an organization dedicated to powering equitable access to AI technology through education and integration. Their mission is to keep users' minds active and sharp by challenging their memory, language, and critical thinking skills. ๎cite๎turn0search0๎๎
References
This model card provides an overview of Professor Synapse, its development, intended use, and ethical considerations. Users are encouraged to review this information to understand the model's capabilities and limitations.๎
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 19
Model tree for SynapticLabs/ProfSynapse_v01
Base model
unsloth/mistral-7b-v0.3
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="SynapticLabs/ProfSynapse_v01", filename="", )