Instructions to use SlayThat/NikiAI-Survival with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SlayThat/NikiAI-Survival with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SlayThat/NikiAI-Survival
# Run inference directly in the terminal:
llama cli -hf SlayThat/NikiAI-Survival

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SlayThat/NikiAI-Survival
# Run inference directly in the terminal:
llama cli -hf SlayThat/NikiAI-Survival

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 SlayThat/NikiAI-Survival
# Run inference directly in the terminal:
./llama-cli -hf SlayThat/NikiAI-Survival

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 SlayThat/NikiAI-Survival
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SlayThat/NikiAI-Survival

Use Docker

docker model run hf.co/SlayThat/NikiAI-Survival

LM Studio
Jan

vLLM

How to use SlayThat/NikiAI-Survival with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SlayThat/NikiAI-Survival

Ollama
How to use SlayThat/NikiAI-Survival with Ollama:
```
ollama run hf.co/SlayThat/NikiAI-Survival
```

Unsloth Studio

How to use SlayThat/NikiAI-Survival 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 SlayThat/NikiAI-Survival 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 SlayThat/NikiAI-Survival to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SlayThat/NikiAI-Survival to start chatting

Docker Model Runner
How to use SlayThat/NikiAI-Survival with Docker Model Runner:
```
docker model run hf.co/SlayThat/NikiAI-Survival
```

Lemonade

How to use SlayThat/NikiAI-Survival with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SlayThat/NikiAI-Survival

Run and chat with the model

lemonade run user.NikiAI-Survival-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

NikiAI-Survival / README.md

SlayThat

Update README.md

53290e2 verified 7 days ago

preview code

Raw

History Blame Contribute Delete

1.33 kB

	---
	license: llama3.2
	datasets:
	- wikimedia/wikipedia
	language:
	- en
	base_model:
	- meta-llama/Llama-3.2-1B
	pipeline_tag: text-generation
	tags:
	- gguf
	- unsloth
	- survival
	- llama-3
	- q4_k_m
	---
	# NikiAI-Survival (GGUF)

	NikiAI-Survival is a lightweight, domain-adapted language model based on `meta-llama/Llama-3.2-1B`. It is fine-tuned on specialized knowledge covering wilderness survival, first aid, bushcraft, emergency signaling, water purification, and disaster preparedness.

	---

	## Model Details
	* Developed by: SlayThat
	* Base Model: [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)
	* Fine-Tuning Framework: [Unsloth](https://github.com/unslothai/unsloth)
	* Format: GGUF (4-bit medium quantization `Q4_K_M`)
	* Primary Domain: Survival Skills, Wilderness Medicine, Bushcraft, Emergency Preparedness

	---

	## How to Run Locally

	### Option 1: LM Studio
	1. Open LM Studio.
	2. Drag and drop the downloaded `llama-3.2-1b.Q4_K_M.gguf` file directly into the application.
	3. Select the model from the top dropdown menu and start chatting.

	### Option 2: Ollama
	1. Place the `.gguf` file in a dedicated folder.
	2. Create a text file named `Modelfile` in the same directory with this content:
	```dockerfile
	FROM ./llama-3.2-1b.Q4_K_M.gguf
	PARAMETER stop "<\|eot_id\|>"