Instructions to use biustnaspust/Teutonic-III-tukas4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use biustnaspust/Teutonic-III-tukas4 with Transformers:

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

pipe = pipeline("text-generation", model="biustnaspust/Teutonic-III-tukas4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("biustnaspust/Teutonic-III-tukas4")
model = AutoModelForCausalLM.from_pretrained("biustnaspust/Teutonic-III-tukas4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use biustnaspust/Teutonic-III-tukas4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "biustnaspust/Teutonic-III-tukas4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "biustnaspust/Teutonic-III-tukas4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/biustnaspust/Teutonic-III-tukas4

SGLang

How to use biustnaspust/Teutonic-III-tukas4 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 "biustnaspust/Teutonic-III-tukas4" \
    --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": "biustnaspust/Teutonic-III-tukas4",
		"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 "biustnaspust/Teutonic-III-tukas4" \
        --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": "biustnaspust/Teutonic-III-tukas4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use biustnaspust/Teutonic-III-tukas4 with Docker Model Runner:
```
docker model run hf.co/biustnaspust/Teutonic-III-tukas4
```

tukas4

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: whiskeyman/Teutonic-III-v3-2x-1886
    parameters:
      weight: 0.95
  - model: whiskeyman/Teutonic-III-v3-1x-466
    parameters:
      weight: 0.05
merge_method: linear
dtype: bfloat16

Downloads last month: 409

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for biustnaspust/Teutonic-III-tukas4

whiskeyman/Teutonic-III-v3-1x-466

whiskeyman/Teutonic-III-v3-2x-1886

Merge model

this model

Paper for biustnaspust/Teutonic-III-tukas4

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 8