Instructions to use DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps with Transformers:

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

pipe = pipeline("text-generation", model="DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps")
model = AutoModelForCausalLM.from_pretrained("DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps

SGLang

How to use DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps 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 "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps" \
    --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": "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps",
		"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 "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps" \
        --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": "DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps with Docker Model Runner:
```
docker model run hf.co/DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps
```

Self trained microscopic Mamba. Around 2.1G parameters.

The tokenizer is the one from https://huggingface.co/state-spaces/mamba-2.8b-hf.

It is being trained on around 400B tokens and this is step 13.4k.

The evaluation is being conducted now.

License

This model is available under the Apache 2.0 License.

Discord Server

Join our Discord server here.

Feeling Generous? 😊

Eager to buy me a cup of 2$ coffe or iced tea?🍵☕ Sure, here is the link: https://ko-fi.com/drnicefellow. Please add a note on which one you want me to drink?

Downloads last month: 2

Collection including DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps

Microscopic-Mamba-2.1B

Collection

8 items • Updated Apr 6, 2025