Instructions to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with Transformers:

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

pipe = pipeline("text-generation", model="Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix 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 Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Lewdiculous/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Lewdiculous/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M

Use Docker

docker model run hf.co/Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M

LM Studio
Jan

vLLM

How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lewdiculous/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M

SGLang

How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-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/Kunocchini-7b-128k-test-GGUF-Imatrix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with Ollama:
```
ollama run hf.co/Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with Docker Model Runner:
```
docker model run hf.co/Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M
```

Lemonade

How to use Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix:Q4_K_M

Run and chat with the model

lemonade run user.Kunocchini-7b-128k-test-GGUF-Imatrix-Q4_K_M

List all available models

lemonade list

Atomic Chat

Support:
My upload speeds have been cooked and unstable lately.
Realistically I'd need to move to get a better provider.
If you want and you are able to...
You can support my various endeavors here (Ko-fi).
I apologize for disrupting your experience.

GGUF-Imatrix quantizations for Kunocchini-7b-128k-test.

UPDATED: Please download the v2 files that are now available. The new IQ4_NL and IQ4_XS quants were also added.

What does "Imatrix" mean?

It stands for Importance Matrix, a technique used to improve the quality of quantized models.

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.

One of the benefits of using an Imatrix is that it can lead to better model performance, especially when the calibration data is diverse.

More information: [1] [2]

This has been my personal favourite and daily-driver role-play model for a while, so I decided to make new quantizations for it using the full F16-Imatrix data.

SillyTavern preset files are located here.

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

All credits belong to the creator.

Base⇢ GGUF(F16)⇢ GGUF(Quants)

The new IQ3_S merged today 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.

Using llama.cpp-b2254.

For --imatrix data, imatrix-Kunocchini-7b-128k-test-F16.dat was used.

Original model information:

Thanks to @Epiculous for the dope model/ help with llm backends and support overall.

Id like to also thank @kalomaze for the dope sampler additions to ST.

@SanjiWatsuki Thank you very much for the help, and the model!

ST users can find the TextGenPreset in the folder labeled so.

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
        layer_range: [0, 32]
      - model: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
        layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Downloads last month: 2,154

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix

Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context

SanjiWatsuki/Kunoichi-DPO-v2-7B

Merge model

this model

Collection including Lewdiculous/Kunocchini-7b-128k-test-GGUF-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 • 72