Instructions to use Mabeck/Heidrun-Mistral-7B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mabeck/Heidrun-Mistral-7B-chat with Transformers:

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

pipe = pipeline("text-generation", model="Mabeck/Heidrun-Mistral-7B-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mabeck/Heidrun-Mistral-7B-chat")
model = AutoModelForCausalLM.from_pretrained("Mabeck/Heidrun-Mistral-7B-chat")

llama-cpp-python

How to use Mabeck/Heidrun-Mistral-7B-chat with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mabeck/Heidrun-Mistral-7B-chat",
	filename="Heidrun-Mistral-7B-chat-Q6_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Mabeck/Heidrun-Mistral-7B-chat with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K

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 Mabeck/Heidrun-Mistral-7B-chat:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K

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 Mabeck/Heidrun-Mistral-7B-chat:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mabeck/Heidrun-Mistral-7B-chat:Q6_K

Use Docker

docker model run hf.co/Mabeck/Heidrun-Mistral-7B-chat:Q6_K

LM Studio
Jan

vLLM

How to use Mabeck/Heidrun-Mistral-7B-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mabeck/Heidrun-Mistral-7B-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mabeck/Heidrun-Mistral-7B-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mabeck/Heidrun-Mistral-7B-chat:Q6_K

SGLang

How to use Mabeck/Heidrun-Mistral-7B-chat 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 "Mabeck/Heidrun-Mistral-7B-chat" \
    --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": "Mabeck/Heidrun-Mistral-7B-chat",
		"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 "Mabeck/Heidrun-Mistral-7B-chat" \
        --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": "Mabeck/Heidrun-Mistral-7B-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Mabeck/Heidrun-Mistral-7B-chat with Ollama:
```
ollama run hf.co/Mabeck/Heidrun-Mistral-7B-chat:Q6_K
```

Unsloth Studio new

How to use Mabeck/Heidrun-Mistral-7B-chat 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 Mabeck/Heidrun-Mistral-7B-chat 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 Mabeck/Heidrun-Mistral-7B-chat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mabeck/Heidrun-Mistral-7B-chat to start chatting

Docker Model Runner
How to use Mabeck/Heidrun-Mistral-7B-chat with Docker Model Runner:
```
docker model run hf.co/Mabeck/Heidrun-Mistral-7B-chat:Q6_K
```

Lemonade

How to use Mabeck/Heidrun-Mistral-7B-chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mabeck/Heidrun-Mistral-7B-chat:Q6_K

Run and chat with the model

lemonade run user.Heidrun-Mistral-7B-chat-Q6_K

List all available models

lemonade list

Model description

Heidrun-Mistral-7B-chat is a chat-model based on Heidrun-Mistral-7B-base, finetuned on danish-OpenHermes and skoleGPT for a instruction/chat format.

It is a new SOTA Danish open-source LLM and shows very strong performance in logic and reasoning tasks.

Heidrun-7B ranks 1st among Danish open-sourced LLMs based on the ScandEval benchmark and shares 1st place on all Scandinavian languages.

Benchmarks

The following benchmarks have been tested using ScandEval. Rankings don't include merged models and GPT4 and GPT3.5 ranks 1 and 2:

MMLU-da: 35.66%+-0.85%/51.68+-0.63%, ranks 3rd
DANSK: 50.80% ± 2.33% / 34.04% ± 1.76%, ranks 3rd=
Hellaswag-da: 29.18% ± 0.99%/ 46.64% ± 0.76%, ranks 4th

Datasets

This model is trained on Danish instruction datasets danish-OpenHermes and skoleGPT, which have not been safeguarded or alligned.

Most of the data has been machine-translated and may contain incorrect responses.

Samples

This model uses the ChatML format. Using other formats may degrade the model's performance.

Samples from the model using ChatML format:

"<s> <im_start>system 
Du er en AI-hjælper. Du får en opgave fra en bruger hvor du kort og præcist skal forklare svaret. 
<im_end> 
<im_start>user 
Hvilke 3 populære retter findes der i dansk madlavning? 
<im_end> 
<im_start>assistant 
1. Smørrebrød: Smørrebrød er en populær dansk ret, der består af brød med forskellige toppings som røget laks, rejer, ost eller andre ingredienser.

2. Frikadeller: Frikadeller er en traditionel dansk ret lavet af kødboller af kalvekød, svinekød eller lam, krydret med krydderurter og kogt i smør eller olie.

3. Rød kål: Rød kål er en populær side ret i dansk madlavning.
<im_end></s>"

"<s> <im_start>system 
Du er en AI-hjælper. Du får en opgave fra en bruger hvor du kort og præcist skal forklare svaret. 
<im_end> 
<im_start>user 
Hvilke 3 områder skal fokuseres på for at effektivt tackle klimaforandringer? 
<im_end> 
<im_start>assistant 
1. Energiproduktion: Fokus på vedvarende energikilder som sol, vind og vandkraft for at reducere afhængigheden af fossile brændstoffer og minimere drivhusgasemissioner.

2. Transport: Fremme bæredygtige transportformer som offentlig transport, cykling og elektriske køretøjer for at reducere luftforurening og afhængigheden af fossile brændstoffer.

3. Skovbevarelse og affaldshåndtering: Fremme skovbevarelse og bæredygtig skovdrift for at fange kuldioxid og reducere drivhusgasemissioner, samt fremme genbrug og reducere affaldsproduktion for at mindske mængden af drivhusgasemissioner fra affald. 
<im_end></s>"

Uploaded model

Developed by: Mabeck
Finetuned from model : Mabeck/Heidrun-Mistral-7B-base

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 781

Safetensors

Model size

7B params

Tensor type

F16

Model tree for Mabeck/Heidrun-Mistral-7B-chat

Base model

mistralai/Mistral-7B-v0.1

Finetuned

Mabeck/Heidrun-Mistral-7B-base

Quantized

(4)

this model

Quantizations

2 models

Mabeck
/

Heidrun-Mistral-7B-chat