Instructions to use TheDrummer/Behemoth-123B-v2.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheDrummer/Behemoth-123B-v2.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheDrummer/Behemoth-123B-v2.2-GGUF",
	filename="Behemoth-123B-v2f-BF16-00001-of-00006.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 TheDrummer/Behemoth-123B-v2.2-GGUF 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 TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Behemoth-123B-v2.2-GGUF: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 TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Behemoth-123B-v2.2-GGUF: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 TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Behemoth-123B-v2.2-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheDrummer/Behemoth-123B-v2.2-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 TheDrummer/Behemoth-123B-v2.2-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 TheDrummer/Behemoth-123B-v2.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheDrummer/Behemoth-123B-v2.2-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TheDrummer/Behemoth-123B-v2.2-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Behemoth-123B-v2.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Behemoth-123B-v2.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Behemoth-123B-v2.2-GGUF-Q4_K_M

List all available models

lemonade list

Nbv9pQ88Xb

Nearly 2500 members strong 💪

Now with more channels! A hub for creatives and makers alike!

BeaverAI proudly presents...

The finetune that made people buy another 3090...

Behemoth 123B v2.2 🦣 - Chaos Edition

Nothing in the void is foreign to us. The place we go is the place we belong.

Description

Behemoth v2.x is a finetune of the new Largestral 2411 with system prompt support. Testers have noted that everything felt improved.

Usage

Testers say this frankenformat maximizes the model's potential: Metharme with Mistral's new system tokens

[SYSTEM_PROMPT] <|system|>{{system_message}}[/SYSTEM_PROMPT]<|user|>{{user_message}}<|model|>{{assistant_message}}
<|system|>[SYSTEM_PROMPT] {{system_message}}[/SYSTEM_PROMPT]<|user|>{{user_message}}<|model|>{{assistant_message}}

Take note that the opening system tag SHOULD ALWAYS have a leading whitespace after it.

Complete SillyTavern Settings in BeaverAI Club: https://discord.com/channels/1238219753324281886/1309968730301792370/1309968730301792370

Mirror: https://rentry.org/cd32disa

Versions

v2.0 is equivalent to Behemoth v1.0 (Classic)
- Claude-like creativity and prose
- Very familiar style
- Solid for all tasks
v2.1 is equivalent to Behemoth v1.1 (Creative Boost)
- Creative and lively
- Unique prose
- Balanced enough for RP and other tasks
v2.2 is a cranked up version of Behemoth v2.1 (Unhinged)
- Creatively unhinged
- Constantly unique prose
- May be too chaotic for strict RP, thrives in adventure / story

Special Thanks

Thank you to each and everyone who donated/subscribed in Ko-Fi 🙇 I hope to never disappoint!

Toasty Pigeon
theguywhogamesalot
Grozi
F
Marinara
Ko-fi Supporter
Grozi
Phaelon
ONTHEREDTEAM 
EvarinSharath'fe(USM-Valor)
Silva
Dakkidaze
AlexTheVP
Pseudo
Kistara
Dr. Fjut
Grozi 🥈
KinjiHakari777
dustywintr
Syd
HumbleConsumer
Syd
Ko-fi Supporter
Arkamist
joe 🥇
Toad
Lied
Konnect
Kistara
Grozi 🥉
SleepDeprived3
Luigi
Nestor

https://ko-fi.com/thedrummer/leaderboard

Finetuned by yours truly,
Drummer

Thank you Gargy for the GPUs!

Downloads last month: 134

GGUF

Model size

123B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

TheDrummer
/

Behemoth-123B-v2.2-GGUF