Instructions to use H-D-T/Buzz-3b-small-v0.6.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use H-D-T/Buzz-3b-small-v0.6.3 with Transformers:

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

pipe = pipeline("text-generation", model="H-D-T/Buzz-3b-small-v0.6.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("H-D-T/Buzz-3b-small-v0.6.3")
model = AutoModelForCausalLM.from_pretrained("H-D-T/Buzz-3b-small-v0.6.3")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use H-D-T/Buzz-3b-small-v0.6.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "H-D-T/Buzz-3b-small-v0.6.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "H-D-T/Buzz-3b-small-v0.6.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/H-D-T/Buzz-3b-small-v0.6.3

SGLang

How to use H-D-T/Buzz-3b-small-v0.6.3 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 "H-D-T/Buzz-3b-small-v0.6.3" \
    --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": "H-D-T/Buzz-3b-small-v0.6.3",
		"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 "H-D-T/Buzz-3b-small-v0.6.3" \
        --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": "H-D-T/Buzz-3b-small-v0.6.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use H-D-T/Buzz-3b-small-v0.6.3 with Docker Model Runner:
```
docker model run hf.co/H-D-T/Buzz-3b-small-v0.6.3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Buzz-3b-Small-v0.6.3

This model is a intermediate checkpoint of H-D-T/Buzz-3b-small-v0.6.3 trained on

datasets:

path: H-D-T/Buzz-slice-1-10 type: sharegpt
path: H-D-T/Buzz-slice-2-10 type: sharegpt

chat_template: llama3

Model description

Buzz small 0.6.3 is an intermediate checkpoint 2/10ths of the way through the buzz dataset, its trained using the llama 3 chat template for only a single epoch over approximately 6.2 million examples

Intended uses & limitations

the model behaves in a standard 'chat' style, performing the normal tasks an assistant model would typically be expected to perform, often quite well.

it has the ability to write code, play characters, break down tasks, provide tutorials, step by step walkthroughs, data analysis, and perform mathematical calculations.

the models outputs may be inaccurate to some degree.

tutorial

[will update]

Framework versions

unsloth 2.4.0
axolotl 4.0.0
Transformers 4.40.2
Pytorch 2.1.2+cu118
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 13

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for H-D-T/Buzz-3b-small-v0.6.3

Unable to build the model tree, the base model loops to the model itself. Learn more.