Instructions to use qikp/hummingbird-2-125m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qikp/hummingbird-2-125m with Transformers:

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

pipe = pipeline("text-generation", model="qikp/hummingbird-2-125m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qikp/hummingbird-2-125m")
model = AutoModelForCausalLM.from_pretrained("qikp/hummingbird-2-125m", device_map="auto")
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 Settings

vLLM

How to use qikp/hummingbird-2-125m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qikp/hummingbird-2-125m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qikp/hummingbird-2-125m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qikp/hummingbird-2-125m

SGLang

How to use qikp/hummingbird-2-125m 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 "qikp/hummingbird-2-125m" \
    --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": "qikp/hummingbird-2-125m",
		"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 "qikp/hummingbird-2-125m" \
        --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": "qikp/hummingbird-2-125m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qikp/hummingbird-2-125m with Docker Model Runner:
```
docker model run hf.co/qikp/hummingbird-2-125m
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A newer version of this model is available: qikp/hummingbird-3-110m

Hummingbird

🎉 You are looking at Hummingbird 2, trained on a much more efficient corpus, achieving similar performance with 3x less parameters!

Hummingbird is a GPT-2 derivative trained to be conversational.

Training

The model was trained using the paged_adamw_8bit optimizer, gradient checkpointing, 500 steps, 1 batch size, and 4 gradient accumulation steps.

Datasets

The training corpus is made up of:

First 1400 rows of qikp/reborn-5k-no-thoughts
First 500 rows of HuggingFaceTB/smol-smoltalk
First 100 rows of HuggingFaceTB/everyday-conversations-llama3.1-2k

The train / train_sft splits were used.

Chat template

The Zephyr chat template was used.

Limitations

The model frequently outputs incorrect information, confirmation with a larger, mature model is advised.

Benchmark

This model was tested against GAIA and compared using embeddings. See the results here.

Downloads last month: 13

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for qikp/hummingbird-2-125m

Base model

openai-community/gpt2

Finetuned

(2252)

this model

Quantizations

2 models

qikp
/

hummingbird-2-125m