Instructions to use nkthebass/tinybrainbot-3m-loop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nkthebass/tinybrainbot-3m-loop with Transformers:

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

pipe = pipeline("text-generation", model="nkthebass/tinybrainbot-3m-loop", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nkthebass/tinybrainbot-3m-loop", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nkthebass/tinybrainbot-3m-loop with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nkthebass/tinybrainbot-3m-loop"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nkthebass/tinybrainbot-3m-loop",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nkthebass/tinybrainbot-3m-loop

SGLang

How to use nkthebass/tinybrainbot-3m-loop 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 "nkthebass/tinybrainbot-3m-loop" \
    --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": "nkthebass/tinybrainbot-3m-loop",
		"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 "nkthebass/tinybrainbot-3m-loop" \
        --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": "nkthebass/tinybrainbot-3m-loop",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nkthebass/tinybrainbot-3m-loop with Docker Model Runner:
```
docker model run hf.co/nkthebass/tinybrainbot-3m-loop
```

tinybrainbot-3m-loop / configuration_tbbloop.py

nkthebass

TinyBrainBot-3M-Loop: 2.96M recurrent-depth model, final checkpoint

3020d73 verified 2 days ago

Raw History Blame Contribute Delete

457 Bytes

"""Config for TinyBrainBot recurrent-depth models (fields mirror the native TinyBrainBotConfig)."""
from transformers import PretrainedConfig


class TBBLoopConfig(PretrainedConfig):
    model_type = "tbbloop"

    def __init__(self, native=None, eval_loops=0, tie_word_embeddings=True, **kwargs):
        self.native = native or {}
        self.eval_loops = eval_loops
        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)

	"""Config for TinyBrainBot recurrent-depth models (fields mirror the native TinyBrainBotConfig)."""
	from transformers import PretrainedConfig


	class TBBLoopConfig(PretrainedConfig):
	model_type = "tbbloop"

	def __init__(self, native=None, eval_loops=0, tie_word_embeddings=True, **kwargs):
	self.native = native or {}
	self.eval_loops = eval_loops
	super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)