Instructions to use HyperbeeAI/Tulpar-7b-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HyperbeeAI/Tulpar-7b-v0 with Transformers:

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

pipe = pipeline("text-generation", model="HyperbeeAI/Tulpar-7b-v0")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HyperbeeAI/Tulpar-7b-v0")
model = AutoModelForCausalLM.from_pretrained("HyperbeeAI/Tulpar-7b-v0", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HyperbeeAI/Tulpar-7b-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HyperbeeAI/Tulpar-7b-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HyperbeeAI/Tulpar-7b-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HyperbeeAI/Tulpar-7b-v0

SGLang

How to use HyperbeeAI/Tulpar-7b-v0 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 "HyperbeeAI/Tulpar-7b-v0" \
    --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": "HyperbeeAI/Tulpar-7b-v0",
		"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 "HyperbeeAI/Tulpar-7b-v0" \
        --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": "HyperbeeAI/Tulpar-7b-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HyperbeeAI/Tulpar-7b-v0 with Docker Model Runner:
```
docker model run hf.co/HyperbeeAI/Tulpar-7b-v0
```

Tulpar-7b-v0

Commit History

Aug 13, 2025

05:42
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
cb8b501

Sep 13, 2023

19:04
Update README.md

ekurtulus

7caa5fc

Aug 28, 2023

04:45
Rename tulpar-v2-lowpoly.png to tulpar.png

ekurtulus

72a3997
04:44
Upload tulpar-v2-lowpoly.png

ekurtulus

4b8d51d
04:44
Delete tulpar.png

ekurtulus

bd3ada4

Aug 27, 2023

07:03
Update README.md

ekurtulus

5a3a03b

Aug 26, 2023

14:54
Update README.md

ekurtulus

c5dfc55
11:24
Update README.md

ekurtulus

f21a192
11:23
Update README.md

ekurtulus

98b5459
11:00
Update README.md

ekurtulus

d7c2bc5
09:50
Update README.md

ekurtulus

aaa83be
09:34
Create README.md

ekurtulus

3080190
09:26
Upload tulpar.png

ekurtulus

b08f63f

Aug 23, 2023

11:30
Update config.json

ekurtulus

acb6497
11:08
Upload tokenizer

ekurtulus

00012d8
11:07
Upload LlamaForCausalLM

ekurtulus

ef5454e
10:13
initial commit

ekurtulus

47b93c2

Commit History

Aug 13, 2025

Adding `safetensors` variant of this model⁠

Sep 13, 2023

Update README.md

Aug 28, 2023

Rename tulpar-v2-lowpoly.png to tulpar.png

Upload tulpar-v2-lowpoly.png

Delete tulpar.png

Aug 27, 2023

Update README.md

Aug 26, 2023

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Create README.md

Upload tulpar.png

Aug 23, 2023

Update config.json

Upload tokenizer

Upload LlamaForCausalLM

initial commit