Instructions to use HyperbeeAI/Tulpar-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HyperbeeAI/Tulpar-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="HyperbeeAI/Tulpar-7b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HyperbeeAI/Tulpar-7b-v2")
model = AutoModelForCausalLM.from_pretrained("HyperbeeAI/Tulpar-7b-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HyperbeeAI/Tulpar-7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HyperbeeAI/Tulpar-7b-v2"
# 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-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HyperbeeAI/Tulpar-7b-v2

SGLang

How to use HyperbeeAI/Tulpar-7b-v2 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-v2" \
    --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-v2",
		"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-v2" \
        --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-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HyperbeeAI/Tulpar-7b-v2 with Docker Model Runner:
```
docker model run hf.co/HyperbeeAI/Tulpar-7b-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

Tulpar-7b is a Mistral-7b-based model trained by HyperbeeAI. Training is done on a filtered and preprocessed instruction finetuning dataset that includes GPT-4 generated and generally curated datasets like Airoboros and Platypus.

Example Usage

Loading the model:

from transformers import AutoTokenizer, AutoModelForCausalLM

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

You can run inference with both of the following prompts:

input_text="What is deep learning?"
prompt = f"### User: {input_text}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=512)
print(tokenizer.decode(output[0]))

input_text="What is deep learning?"
prompt = f"Question: {input_text}\n\nAnswer:"
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=512)
print(tokenizer.decode(output[0]))

or use ChatML format.

Ethical Considerations and Limitations

Tulpar is a technology with potential risks and limitations. This model is finetuned only in English and all language-related scenarios are not covered. As HyperbeeAI, we neither guarantee ethical, accurate, unbiased, objective responses nor endorse its outputs. Before deploying this model, you are advised to make safety tests for your use case.

Downloads last month: 209

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for HyperbeeAI/Tulpar-7b-v2

Merges

1 model

Quantizations

1 model