Instructions to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix", dtype="auto")

llama-cpp-python

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix",
	filename="Erosumika-7B-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix: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 Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix: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 Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M

Use Docker

docker model run hf.co/Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M

LM Studio
Jan

vLLM

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M

SGLang

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with Ollama:
```
ollama run hf.co/Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
```

Unsloth Studio

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix 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 Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix 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 Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix to start chatting

Atomic Chat new
Docker Model Runner
How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with Docker Model Runner:
```
docker model run hf.co/Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M
```

Lemonade

How to use Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix:Q4_K_M

Run and chat with the model

lemonade run user.Erosumika-7B-GGUF-IQ-Imatrix-Q4_K_M

List all available models

lemonade list

GGUF-Imatrix quantizations for localfultonextractor/Erosumika-7B.

All credits belong to the author.

If you like these also check out FantasiaFoundry's GGUF-Quantization-Script.

What does "Imatrix" mean?

It stands for Importance Matrix, a technique used to improve the quality of quantized models.
[1]
The Imatrix is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance and lead to better performance, especially when the calibration data is diverse.
[2]

For --imatrix data, included imatrix.dat was used.

Using llama.cpp-b2327:

Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)

The new IQ3_S quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in koboldcpp-1.59.1 or higher.

If you want any specific quantization to be added, feel free to ask.

Original model information:

Erosumika-7B

This is an attempt to create a model that combines multiple "established" 7Bs and a very small WIP private dataset with Eros' raw creative power. In terms of instruction formats, ChatML and Alpaca work best. The merge isn't purely ChatML, and as such, my previous attempts to integrate it with ChatML strings out of the box were Sisyphean and uninformed.

GGUF

exl2, 4bpw

exl2, 6bpw

Merge config.yml:

I was asked to upload the merge configuration I used, sadly the one for the 'sumitest02' model is lost to time, like tears in rain:

  - sources:
      - model: localfultonextractor/sumitest02
        layer_range: [0, 32]
      - model: tavtav/eros-7b-test
        layer_range: [0, 32]
merge_method: slerp
base_model: localfultonextractor/sumitest02
parameters:
  t:
    - filter: self_attn
      value: [0, 0.2, 0.4, 0.55, 0.8]
    - filter: mlp
      value: [0.7, 0.3, 0.4, 0.3, 0]
    - value: 0.37 # fallback for rest of tensors
dtype: float16

Downloads last month: 106

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Collection including Lewdiculous/Erosumika-7B-GGUF-IQ-Imatrix

Quantized Models (GGUF, IQ, Imatrix)

Collection

Various GGUF quantizations of small models. Models with a "checkmark" are personal favorites. An "orange arrow" means it's being uploaded. • 97 items • Updated Mar 2 • 71