Instructions to use abideen/Bitnet-Llama-70M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abideen/Bitnet-Llama-70M with Transformers:

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

pipe = pipeline("text-generation", model="abideen/Bitnet-Llama-70M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abideen/Bitnet-Llama-70M")
model = AutoModelForCausalLM.from_pretrained("abideen/Bitnet-Llama-70M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abideen/Bitnet-Llama-70M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abideen/Bitnet-Llama-70M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abideen/Bitnet-Llama-70M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abideen/Bitnet-Llama-70M

SGLang

How to use abideen/Bitnet-Llama-70M 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 "abideen/Bitnet-Llama-70M" \
    --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": "abideen/Bitnet-Llama-70M",
		"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 "abideen/Bitnet-Llama-70M" \
        --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": "abideen/Bitnet-Llama-70M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abideen/Bitnet-Llama-70M with Docker Model Runner:
```
docker model run hf.co/abideen/Bitnet-Llama-70M
```

abideen commited on Apr 4, 2024

Commit

1759db7

verified ·

1 Parent(s): d87f477

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ tags:
 Bitnet-LLama-70M is a 70M parameter model trained using the method described in [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764).
-It was trained on the subset of the [HuggingFaceTB/cosmopedia](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) dataset. This is just a small experiment to try out BitNet.
-Bitnet-LLama-70M was trained
 Wandb training report is as follows:

 Bitnet-LLama-70M is a 70M parameter model trained using the method described in [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764).
+It was trained on the subset of the [HuggingFaceTB/cosmopedia](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) dataset. This is just a small experiment to try out BitNet. Bitnet-LLama-70M was trained for 2 epochs on 1xA100.
+This model is just an experiment and you might not get good results while chatting with it due to smaller model size and less training.
 Wandb training report is as follows: