Mamba
Collection
Mamba checkpoints compatible with transformers • 6 items • Updated • 2
How to use from
SGLangUse 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 "ArthurZ/mamba-130m" \
--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": "ArthurZ/mamba-130m",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
>>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer
>>> import torch
>>> tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b", padding_side = "left")
>>> tokenizer.pad_token = tokenizer.eos_token
>>> model = MambaForCausalLM.from_pretrained("state-spaces/mamba-130m", vocab_size=50280, num_hidden_layers=24, torch_dtype=torch.float32)
>>> model.config.use_cache = True
>>> input_ids = tokenizer(["Hey how are you doing?", "Explain how soy sauce is made"], padding=True, return_tensors= "pt")["input_ids"]
>>> out = model.generate(input_ids, max_new_tokens=10)
>>> print(tokenizer.batch_decode(out))
["<|endoftext|>Hey how are you doing?\n\nI'm a newbie to the game", 'Explain how soy sauce is made.\n\n1. Add the soy sauce to']
- Downloads last month
- 3,545
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ArthurZ/mamba-130m" \ --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": "ArthurZ/mamba-130m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'