Instructions to use dkp2701/survuday_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use dkp2701/survuday_v1 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="dkp2701/survuday_v1", filename="survuday_v1.Q4_K_M.gguf", )
llm.create_chat_completion( messages = "{\n \"question\": \"What is my name?\",\n \"context\": \"My name is Clara and I live in Berkeley.\"\n}" ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use dkp2701/survuday_v1 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf dkp2701/survuday_v1:Q4_K_M # Run inference directly in the terminal: llama-cli -hf dkp2701/survuday_v1:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf dkp2701/survuday_v1:Q4_K_M # Run inference directly in the terminal: llama-cli -hf dkp2701/survuday_v1:Q4_K_M
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 dkp2701/survuday_v1:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf dkp2701/survuday_v1:Q4_K_M
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 dkp2701/survuday_v1:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf dkp2701/survuday_v1:Q4_K_M
Use Docker
docker model run hf.co/dkp2701/survuday_v1:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use dkp2701/survuday_v1 with Ollama:
ollama run hf.co/dkp2701/survuday_v1:Q4_K_M
- Unsloth Studio new
How to use dkp2701/survuday_v1 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 dkp2701/survuday_v1 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 dkp2701/survuday_v1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for dkp2701/survuday_v1 to start chatting
- Docker Model Runner
How to use dkp2701/survuday_v1 with Docker Model Runner:
docker model run hf.co/dkp2701/survuday_v1:Q4_K_M
- Lemonade
How to use dkp2701/survuday_v1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dkp2701/survuday_v1:Q4_K_M
Run and chat with the model
lemonade run user.survuday_v1-Q4_K_M
List all available models
lemonade list
survuday
- Mental Health Support Chatbot developed by fine-tuning Large Language Model - Llama 3.2
- Version 1
Other Model Versions Huggingface Repo
- survuday_v2: https://huggingface.co/dkp2701/survuday_v2
- survuday_v3: https://huggingface.co/dkp2701/survuday_v3
Dataset
- Mental Helath-related dialogue data were taken from kaggle and apart from that non-mental health-related conversations for model effectiveness were added manually.
- Non-mental health-related data were added so that the model can get confined to give response only related to mental health conversations.
- Synthetic Therapy Conversations (Kaggle): https://www.kaggle.com/datasets/thedevastator/synthetic-therapy-conversations-dataset
- Downloads last month
- 12
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for dkp2701/survuday_v1
Base model
meta-llama/Llama-3.2-3B