Instructions to use lmg-anon/vntl-gemma2-2b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use lmg-anon/vntl-gemma2-2b-gguf with PEFT:
```
Task type is invalid.
```

How to use lmg-anon/vntl-gemma2-2b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lmg-anon/vntl-gemma2-2b-gguf",
	filename="vntl-gemma2-2b-hf-q6_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lmg-anon/vntl-gemma2-2b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K
# Run inference directly in the terminal:
llama-cli -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K
# Run inference directly in the terminal:
llama-cli -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K

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 lmg-anon/vntl-gemma2-2b-gguf:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K

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 lmg-anon/vntl-gemma2-2b-gguf:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmg-anon/vntl-gemma2-2b-gguf:Q6_K

Use Docker

docker model run hf.co/lmg-anon/vntl-gemma2-2b-gguf:Q6_K

LM Studio
Jan
Ollama
How to use lmg-anon/vntl-gemma2-2b-gguf with Ollama:
```
ollama run hf.co/lmg-anon/vntl-gemma2-2b-gguf:Q6_K
```

Unsloth Studio

How to use lmg-anon/vntl-gemma2-2b-gguf 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 lmg-anon/vntl-gemma2-2b-gguf 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 lmg-anon/vntl-gemma2-2b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lmg-anon/vntl-gemma2-2b-gguf to start chatting

Docker Model Runner
How to use lmg-anon/vntl-gemma2-2b-gguf with Docker Model Runner:
```
docker model run hf.co/lmg-anon/vntl-gemma2-2b-gguf:Q6_K
```

Lemonade

How to use lmg-anon/vntl-gemma2-2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmg-anon/vntl-gemma2-2b-gguf:Q6_K

Run and chat with the model

lemonade run user.vntl-gemma2-2b-gguf-Q6_K

List all available models

lemonade list

Summary

his repository contains some GGUF quantizations of the merged VNTL Gemma2 2B lora, created using the VNTL 3.1 dataset.

The purpose of this model is to improve Gemma2's performance at translating Japanese visual novels to English.

For more information about this model, please check out the original repository.

Translation Prompt

This is an prompt example for translation:

<<METADATA>>
[character] Name: Uryuu Shingo (瓜生 新吾) | Gender: Male | Aliases: Onii-chan (お兄ちゃん)
[character] Name: Uryuu Sakuno (瓜生 桜乃) | Gender: Female
<<TRANSLATE>>
<<JAPANESE>>
[桜乃]: 『……ごめん』
<<ENGLISH>>
[Sakuno]: 『... Sorry.』<eos>
<<JAPANESE>>
[新吾]: 「ううん、こう言っちゃなんだけど、迷子でよかったよ。桜乃は可愛いから、いろいろ心配しちゃってたんだぞ俺」
<<ENGLISH>>

The generated translation for that prompt, with temperature 0, is:

[Shingo]: 「No, I'm glad you got lost. You were so cute that it made me worry.」

Downloads last month: 20

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

6-bit

8-bit

Model tree for lmg-anon/vntl-gemma2-2b-gguf

Base model

google/gemma-2-2b

Finetuned

rinna/gemma-2-baku-2b

Adapter

(3)

this model

lmg-anon
/

vntl-gemma2-2b-gguf

Summary

Translation Prompt

Model tree for lmg-anon/vntl-gemma2-2b-gguf

Dataset used to train lmg-anon/vntl-gemma2-2b-gguf