Instructions to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF",
	filename="SauerkrautLM-UNA-SOLAR-Instruct.Q2_K.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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-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 QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SauerkrautLM-UNA-SOLAR-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/SauerkrautLM-UNA-SOLAR-Instruct-GGUF

This is quantized version of Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct created using llama.cpp

Original Model Card

SauerkrautLM-UNA-SOLAR-Instruct

This is the model for SauerkrautLM-UNA-SOLAR-Instruct. I used mergekit to merge models.

🥳 As of December 24 2023, this model holds the first place position on the Open LLM Leaderboard.

Screenshot

Prompt Template(s)

### User:
{user}

### Assistant:
{asistant}

Yaml Config to reproduce

slices:
  - sources:
      - model: VAGOsolutions/SauerkrautLM-SOLAR-Instruct
        layer_range: [0, 48]
      - model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
        layer_range: [0, 48]

merge_method: slerp
base_model: upstage/SOLAR-10.7B-Instruct-v1.0

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 # fallback for rest of tensors
tokenizer_source: union

dtype: bfloat16

Quantizationed versions

Quantizationed versions of this model is available thanks to TheBloke.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.26
AI2 Reasoning Challenge (25-Shot)	70.90
HellaSwag (10-Shot)	88.30
MMLU (5-Shot)	66.15
TruthfulQA (0-shot)	71.80
Winogrande (5-shot)	83.74
GSM8k (5-shot)	64.67

If you would like to support me:

☕ Buy Me a Coffee

Downloads last month: 34

GGUF

Model size

11B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

70.900
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.300
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

66.150
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

71.800
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.740
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

64.670