Instructions to use arzeth/TowerInstruct-7B-v0.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arzeth/TowerInstruct-7B-v0.2-GGUF with Transformers:

# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("translation", model="arzeth/TowerInstruct-7B-v0.2-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("arzeth/TowerInstruct-7B-v0.2-GGUF", dtype="auto")

llama-cpp-python

How to use arzeth/TowerInstruct-7B-v0.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="arzeth/TowerInstruct-7B-v0.2-GGUF",
	filename="TowerInstruct-7B-v0.2.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use arzeth/TowerInstruct-7B-v0.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
# Run inference directly in the terminal:
llama-cli -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_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 arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_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 arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M

Use Docker

docker model run hf.co/arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M

LM Studio
Jan
Ollama
How to use arzeth/TowerInstruct-7B-v0.2-GGUF with Ollama:
```
ollama run hf.co/arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
```

Unsloth Studio

How to use arzeth/TowerInstruct-7B-v0.2-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 arzeth/TowerInstruct-7B-v0.2-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 arzeth/TowerInstruct-7B-v0.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arzeth/TowerInstruct-7B-v0.2-GGUF to start chatting

Docker Model Runner
How to use arzeth/TowerInstruct-7B-v0.2-GGUF with Docker Model Runner:
```
docker model run hf.co/arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M
```

Lemonade

How to use arzeth/TowerInstruct-7B-v0.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arzeth/TowerInstruct-7B-v0.2-GGUF:IQ3_M

Run and chat with the model

lemonade run user.TowerInstruct-7B-v0.2-GGUF-IQ3_M

List all available models

lemonade list

Model Info

Model creator: Unbabel
Original card (has more info): https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2
Languages: English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian.
Context size: 4096, but according to the model's card it was trained with max_seq_length: 2048, so make sure your input is ≤2048 tokens (is that ~1500 words?).
Template: The model was trained using the ChatML prompt templates WITHOUT ANY SYSTEM PROMPTS !!!, i.e. there's no <|im_start|>system, it's just

<|im_start|>user
{USER PROMPT}<|im_end|>
<|im_start|>assistant
{MODEL RESPONSE}<|im_end|>
<|im_start|>user
[...]

Quantization info

I didn't use imatrix because I have no idea if they are okay for non-general-purpose LLMs.

Quantized with llama.cpp @ 4c4cb30736582cacb1a164a9d4bc8e17b1014be7 (2024-02-24).

IQ3_M requires minimum 4c4cb30736582cacb1a164a9d4bc8e17b1014be7

Licensing

These .gguf files themselves are under CC-0 (i.e. public domain).

TowerInstruct-7B-v0.2 itself is under CC-BY-NC-4.0 ("NC" in "CC-BY-NC-4.0" means "non-commercial" which is legally ambiguous),

but it is based on Llama 2 model which is licensed under the LLAMA 2 Community License (Copyright © Meta Platforms, Inc. All Rights Reserved.) whose TL;DR is you may not use it for bullying, military, and criminal activity.

Downloads last month: 67

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for arzeth/TowerInstruct-7B-v0.2-GGUF

Base model

Unbabel/TowerInstruct-7B-v0.2

Quantized

(7)

this model