Instructions to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix with Transformers:

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

pipe = pipeline("text-generation", model="Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-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/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Lewdiculous/Prima-LelantaclesV6-7b-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 serve -hf Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Lewdiculous/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Lewdiculous/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M

Use Docker

docker model run hf.co/Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M

LM Studio
Jan

vLLM

How to use Lewdiculous/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M

SGLang

How to use Lewdiculous/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-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/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/Prima-LelantaclesV6-7b-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/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix with Ollama:
```
ollama run hf.co/Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
```

Unsloth Studio

How to use Lewdiculous/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-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/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix to start chatting

Docker Model Runner
How to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix with Docker Model Runner:
```
docker model run hf.co/Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M
```

Lemonade

How to use Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lewdiculous/Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix:Q4_K_M

Run and chat with the model

lemonade run user.Prima-LelantaclesV6-7b-GGUF-IQ-Imatrix-Q4_K_M

List all available models

lemonade list

Atomic Chat

GGUF-Imatrix quantizations for Test157t/Prima-LelantaclesV6-7b.

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].

For --imatrix data, imatrix-Prima-LelantaclesV6-7b-F16.dat was used.

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

Using llama.cpp-b2294.

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.

All credits belong to the creator.

Original model information:

This model was merged using the DARE TIES

Models Merged

The following models were included in the merge:

Test157t/West-Pasta-Lake-7b + Test157t/Lelantacles6-Experiment26-7B

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: Test157t/Lelantacles6-Experiment26-7B
parameters:
  normalize: true
models:
  - model: Test157t/West-Pasta-Lake-7b
    parameters:
      weight: 1
  - model: Test157t/Lelantacles6-Experiment26-7B
    parameters:
      weight: 1
dtype: float16