Instructions to use Q-bert/Mamba-370M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Q-bert/Mamba-370M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Q-bert/Mamba-370M", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Q-bert/Mamba-370M", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Q-bert/Mamba-370M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Q-bert/Mamba-370M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Q-bert/Mamba-370M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Q-bert/Mamba-370M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Q-bert/Mamba-370M
- SGLang
How to use Q-bert/Mamba-370M 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 "Q-bert/Mamba-370M" \ --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": "Q-bert/Mamba-370M", "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 "Q-bert/Mamba-370M" \ --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": "Q-bert/Mamba-370M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Q-bert/Mamba-370M with Docker Model Runner:
docker model run hf.co/Q-bert/Mamba-370M
File size: 1,312 Bytes
1a7c8cc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | import math
from typing import Optional , Union
from transformers import PretrainedConfig
class MambaConfig(PretrainedConfig):
model_type = "mamba"
def __init__(
self,
vocab_size=50277,
d_state=16,
d_model=2560,
d_conv=4,
expand=2,
conv_bias=True,
bias=False,
n_layer=64,
dt_rank: Union[int, str] = "auto",
pad_vocab_size_multiple=8,
initializer_range=0.02,
**kwargs,
):
self.vocab_size = vocab_size
self.n_layer= n_layer
self.conv_bias = conv_bias
self.expand = expand
self.pad_vocab_size_multiple = pad_vocab_size_multiple
self.d_conv = d_conv
self.d_model = d_model
self.d_state = d_state
self.d_inner = int(self.expand * self.d_model)
self.dt_rank = dt_rank
self.initializer_range = initializer_range
self.bias = bias
if self.dt_rank == 'auto':
self.dt_rank = math.ceil(self.d_model / 16)
if self.vocab_size % self.pad_vocab_size_multiple != 0:
self.vocab_size += (self.pad_vocab_size_multiple
- self.vocab_size % self.pad_vocab_size_multiple)
super().__init__(
**kwargs,
) |