Instructions to use winhsss/Nina_model_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use winhsss/Nina_model_v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="winhsss/Nina_model_v2",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use winhsss/Nina_model_v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf winhsss/Nina_model_v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf winhsss/Nina_model_v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf winhsss/Nina_model_v2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf winhsss/Nina_model_v2: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 winhsss/Nina_model_v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf winhsss/Nina_model_v2: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 winhsss/Nina_model_v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf winhsss/Nina_model_v2:Q4_K_M

Use Docker

docker model run hf.co/winhsss/Nina_model_v2:Q4_K_M

LM Studio
Jan
Ollama
How to use winhsss/Nina_model_v2 with Ollama:
```
ollama run hf.co/winhsss/Nina_model_v2:Q4_K_M
```

Unsloth Studio

How to use winhsss/Nina_model_v2 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 winhsss/Nina_model_v2 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 winhsss/Nina_model_v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for winhsss/Nina_model_v2 to start chatting

Atomic Chat new
Docker Model Runner
How to use winhsss/Nina_model_v2 with Docker Model Runner:
```
docker model run hf.co/winhsss/Nina_model_v2:Q4_K_M
```

Lemonade

How to use winhsss/Nina_model_v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull winhsss/Nina_model_v2:Q4_K_M

Run and chat with the model

lemonade run user.Nina_model_v2-Q4_K_M

List all available models

lemonade list

Nina_model_v2 / Modelfile

winhsss

(Trained with Unsloth)

de4aebe verified 11 months ago

raw

history blame contribute delete

886 Bytes

	FROM /content/winhsss/Nina_model_v2/unsloth.F16.gguf

	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>{{ end }}{{ if .Prompt }}
	<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>{{ end }}
	<\|im_start\|>assistant
	{{ .Response }}<\|im_end\|><\|end_of_text\|>"""

	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|start_header_id\|>"
	PARAMETER stop "<\|end_header_id\|>"
	PARAMETER stop "<\|end_of_text\|>"
	PARAMETER stop "<\|reserved_special_token_"
	PARAMETER temperature 1.5
	PARAMETER min_p 0.1
	SYSTEM "You are Nina,an assistant, a playful gyaru high school anime girl who likes manga, teases the main character, and always speaks with energetic, playful tone. You will always speak as Nina in first person, never pretending to be the user. You will always call the user ‘Darling’ while replying. Stay fully in character as Nina in every reply, using a mix of playful teasing and warmth."

	FROM /content/winhsss/Nina_model_v2/unsloth.F16.gguf

	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>{{ end }}{{ if .Prompt }}
	<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>{{ end }}
	<\|im_start\|>assistant
	{{ .Response }}<\|im_end\|><\|end_of_text\|>"""

	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|start_header_id\|>"
	PARAMETER stop "<\|end_header_id\|>"
	PARAMETER stop "<\|end_of_text\|>"
	PARAMETER stop "<\|reserved_special_token_"
	PARAMETER temperature 1.5
	PARAMETER min_p 0.1
	SYSTEM "You are Nina,an assistant, a playful gyaru high school anime girl who likes manga, teases the main character, and always speaks with energetic, playful tone. You will always speak as Nina in first person, never pretending to be the user. You will always call the user ‘Darling’ while replying. Stay fully in character as Nina in every reply, using a mix of playful teasing and warmth."