Instructions to use bjoernp/micro-bitllama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bjoernp/micro-bitllama with Transformers:

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

pipe = pipeline("text-generation", model="bjoernp/micro-bitllama", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bjoernp/micro-bitllama", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("bjoernp/micro-bitllama", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bjoernp/micro-bitllama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bjoernp/micro-bitllama

SGLang

How to use bjoernp/micro-bitllama 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 "bjoernp/micro-bitllama" \
    --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": "bjoernp/micro-bitllama",
		"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 "bjoernp/micro-bitllama" \
        --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": "bjoernp/micro-bitllama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bjoernp/micro-bitllama with Docker Model Runner:
```
docker model run hf.co/bjoernp/micro-bitllama
```

BitLLama Micro (Experimental + untrained)

This model contains the modeling code for the 1.58-bit Llama Model following the reference paper: https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf

For more details see: https://github.com/bjoernpl/bitllama

The model was initialized with the following config:

from transformers.models.bitllama import BitLlamaForCausalLM, LlamaConfig

model_config = LlamaConfig(
    bos_token_id=1,
    eos_token_id=2,
    hidden_act="silu",
    hidden_size=512,
    initializer_range=0.02,
    intermediate_size=1365,
    max_position_embeddings=32000,
    num_attention_heads=8,
    num_hidden_layers=12,
    num_key_value_heads=4,
    pretraining_tp=1,
    rms_norm_eps=1e-05,
    rope_scaling=None,
    tie_word_embeddings=True,
    use_cache=True,
    vocab_size=32000,
)

model = BitLlamaForCausalLM._from_config(model_config)
model.push_to_hub("bjoernp/micro-bitllama")

Downloads last month: 1

Safetensors

Model size

51M params

Tensor type

F32