state-spaces/mamba-130m-hf

This repository contains the `transfromers` compatible `mamba-2.8b`. The checkpoints are untouched, but the full `config.json` and tokenizer are pushed to this repo. You need to install `transformers` from `main` until `transformers=4.39.0` is released. pip install git+https://github.com/huggingface/transformers@main We also recommend you to install both `causal_conv_1d` and `mamba-ssm` using: pip install causal-conv1d>=1.2.0 pip install mamba-ssm If any of these two is not installed, the "eager" implementation will be used. Otherwise the more optimised `cuda` kernels will be used. You can use the classic `generate` API: >>> from transformers import MambaConfig, MambaForCausalLM, AutoTokenizer >>> import torch >>> tokenizer = AutoTokenizer.from_pretrained("state-spaces/mamba-130m-hf") >>> model = MambaForCausalLM.from_pretrained("state-spaces/mamba-130m-hf") >>> input_ids = tokenizer("Hey how are you doing?", return_tensors="pt")["input_ids"] >>> out = model.generate(input_ids, max_new_tokens=10) >>> print(tokenizer.batch_decode(out)) ["Hey how are you doing?\n\nI'm so glad you're here."] In order to finetune using the `peft` library, we recommend keeping the model in float32! from datasets import load_dataset from trl import SFTTrainer from peft import LoraConfig from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments tokenizer = AutoTokenizer.from_pretrained("state-spaces/mamba-130m-hf") model = AutoModelForCausalLM.from_pretrained("state-spaces/mamba-130m-hf") dataset = load_dataset("Abirate/english_quotes", split="train") training_args = TrainingArguments( output_dir="./results", num_train_epochs=3, per_device_train_batch_size=4, logging_dir='./logs', logging_steps=10, learning_rate=2e-3 ) lora_config = LoraConfig( r=8, target_modules=["x_proj", "embeddings", "in_proj", "out_proj"], task_type="CAUSAL_LM", bias="none" ) trainer = SFTTrainer( model=model, tokenizer=tokenizer, args=training_args, peft_config=lora_config, train_dataset=dataset, dataset_text_field="quote", ) trainer.train()