StableLM-Tuned-Alpha 7b: sharded checkpoint

This is a sharded checkpoint (with ~4GB shards) of the model. Refer to the original model for all details.

this enables low-RAM loading, i.e. Colab :)

Basic Usage

install transformers, accelerate, and bitsandbytes.

pip install -U -q transformers bitsandbytes accelerate

Load the model in 8bit, then run inference:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "ethzanalytics/stablelm-tuned-alpha-7b-sharded"
tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name, load_in_8bit=True, device_map="auto"
)