Instructions to use LSX-UniWue/LLaMmlein_1B_chat_selected with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LSX-UniWue/LLaMmlein_1B_chat_selected with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("LSX-UniWue/LLaMmlein_1B_prerelease")
model = PeftModel.from_pretrained(base_model, "LSX-UniWue/LLaMmlein_1B_chat_selected")

llama-cpp-python

How to use LSX-UniWue/LLaMmlein_1B_chat_selected with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LSX-UniWue/LLaMmlein_1B_chat_selected",
	filename="LLaMmlein_1B_chat_selected.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LSX-UniWue/LLaMmlein_1B_chat_selected with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LSX-UniWue/LLaMmlein_1B_chat_selected
# Run inference directly in the terminal:
llama-cli -hf LSX-UniWue/LLaMmlein_1B_chat_selected

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LSX-UniWue/LLaMmlein_1B_chat_selected
# Run inference directly in the terminal:
llama-cli -hf LSX-UniWue/LLaMmlein_1B_chat_selected

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 LSX-UniWue/LLaMmlein_1B_chat_selected
# Run inference directly in the terminal:
./llama-cli -hf LSX-UniWue/LLaMmlein_1B_chat_selected

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 LSX-UniWue/LLaMmlein_1B_chat_selected
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LSX-UniWue/LLaMmlein_1B_chat_selected

Use Docker

docker model run hf.co/LSX-UniWue/LLaMmlein_1B_chat_selected

LM Studio
Jan
Ollama
How to use LSX-UniWue/LLaMmlein_1B_chat_selected with Ollama:
```
ollama run hf.co/LSX-UniWue/LLaMmlein_1B_chat_selected
```

Unsloth Studio new

How to use LSX-UniWue/LLaMmlein_1B_chat_selected 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 LSX-UniWue/LLaMmlein_1B_chat_selected 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 LSX-UniWue/LLaMmlein_1B_chat_selected to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LSX-UniWue/LLaMmlein_1B_chat_selected to start chatting

Docker Model Runner
How to use LSX-UniWue/LLaMmlein_1B_chat_selected with Docker Model Runner:
```
docker model run hf.co/LSX-UniWue/LLaMmlein_1B_chat_selected
```

Lemonade

How to use LSX-UniWue/LLaMmlein_1B_chat_selected with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LSX-UniWue/LLaMmlein_1B_chat_selected

Run and chat with the model

lemonade run user.LLaMmlein_1B_chat_selected-{{QUANT_TAG}}

List all available models

lemonade list

LLäMmlein 1B Chat

While the base versions of our LLäMmlein are quite good, our chat versions are research demonstrations and are not ready to be used in settings where close instruction following is necessary. Please check the paper for more details.

This is a chat adapter for the German Tinyllama 1B language model. Find more details on our page and our preprint! We also merged the adapter and converted it to GGUF here.

Run it

import torch
from peft import PeftConfig, PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

torch.manual_seed(42)

# script config
base_model_name = "LSX-UniWue/LLaMmlein_1B_prerelease"
chat_adapter_name = "LSX-UniWue/LLaMmlein_1B_chat_selected"
device = "cuda"  # or mps

# chat history
messages = [
    {
        "role": "user",
        "content": """Na wie geht's?""",
    },
]

# load model
config = PeftConfig.from_pretrained(chat_adapter_name)
base_model = model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype=torch.bfloat16,
    device_map=device,
)
base_model.resize_token_embeddings(32064)
model = PeftModel.from_pretrained(base_model, chat_adapter_name)
tokenizer = AutoTokenizer.from_pretrained(chat_adapter_name)

# encode message in "ChatML" format
chat = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt",
    add_generation_prompt=True,
).to(device)

# generate response
print(
    tokenizer.decode(
        model.generate(
            chat,
            max_new_tokens=300,
            pad_token_id=tokenizer.pad_token_id,
            eos_token_id=tokenizer.eos_token_id,
        )[0],
        skip_special_tokens=False,
    )
)