Instructions to use DavidBrowne17/LlamaThink-8B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidBrowne17/LlamaThink-8B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="DavidBrowne17/LlamaThink-8B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DavidBrowne17/LlamaThink-8B-instruct")
model = AutoModelForCausalLM.from_pretrained("DavidBrowne17/LlamaThink-8B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavidBrowne17/LlamaThink-8B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidBrowne17/LlamaThink-8B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidBrowne17/LlamaThink-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidBrowne17/LlamaThink-8B-instruct

SGLang

How to use DavidBrowne17/LlamaThink-8B-instruct 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 "DavidBrowne17/LlamaThink-8B-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidBrowne17/LlamaThink-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DavidBrowne17/LlamaThink-8B-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidBrowne17/LlamaThink-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DavidBrowne17/LlamaThink-8B-instruct with Docker Model Runner:
```
docker model run hf.co/DavidBrowne17/LlamaThink-8B-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LlamaThink-8b-instruct

LlamaThink-8b-instruct is an instruction-tuned language model built on the LLaMA-3 architecture. It is optimized for generating thoughtful, structured responses using a unique dual-section output format.

GGUF Files

LlamaThink-8b-instruct-GGUF.

Model Details

Architecture: LLaMA-3
Size: 8 billion parameters
License: Apache 2.0

Usage

System Prompt

To ensure the model generates responses in the intended format, use the following system prompt:

Respond in the following format:
<thinking>
...
</thinking>
<answer>
...
</answer>

Example Input

What are the benefits of using LlamaThink-8b-instruct for AI research?

Example Output

<thinking>
LlamaThink-8b-instruct is built on the robust LLaMA-3 architecture, which offers enhanced performance and scalability. Its instruction-tuning ensures it understands complex prompts and provides structured responses. This makes it ideal for research applications where clarity and precision are essential.
</thinking>
<answer>
Using LlamaThink-8b-instruct for AI research provides benefits such as improved contextual understanding, consistent response formatting, and adaptability to various domains. Its open-source Apache 2.0 license also encourages innovation and collaboration.
</answer>

Installation

You can load the model directly from Hugging Face:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "DavidBrowne17/LlamaThink-8B-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Citation

If you use LlamaThink-8b-instruct in your research or applications, please cite it as follows:

@misc{llamathink2025,
  author = {David Browne},
  title = {LlamaThink-8b-instruct},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/DavidBrowne17/LlamaThink-8B-instruct}},
  license = {Apache 2.0}
}