AI Squared's dlite-v2-355m is a large language model which is derived from OpenAI's medium GPT-2 model and fine-tuned on a single GPU on a corpus of 15k records (Databricks' "Dolly 15k" Dataset) to help it exhibit chat-based capabilities.

Just like Databricks' Dolly V2 models, dlite-v2-355m (and all other members of the dlite-v2 family) is licensed for both research and commercial use. We are extremely grateful for the work that Databricks has done to create the databricks-dolly-15k dataset, for without it we would not be able to create and release this model under such an open and permissive license.

While dlite-v2-355m is not a state-of-the-art model, we believe that the level of interactivity that can be achieved on such a small model that is trained so cheaply is important to showcase, as it continues to demonstrate that creating powerful AI capabilities may be much more accessible than previously thought.

dlite-v2-355m is not a state-of-the-art language model. dlite-v2-355m is an experimental technology, and as with any experimental technology, AI Squared urges potential users of this technology to test its capabilities thoroughly before usage. Furthermore, the model can sometimes exhibit undesired behaviors. Some of these behaviors include, but are not limited to: factual inaccuracies, biases, offensive responses, toxicity, and hallucinations. Just as with any other LLM, we advise users of this technology to exercise good judgment when applying this technology.

To use the model with the transformers library on a machine with GPUs, first make sure you have the transformers and accelerate libraries installed. From your terminal, run:

The instruction following pipeline can be loaded using the pipeline function as shown below. This loads a custom InstructionTextGenerationPipeline found in the model repo here, which is why trust_remote_code=True is required. Including torch_dtype=torch.bfloat16 is generally recommended if this type is supported in order to reduce memory usage. It does not appear to impact output quality. It is also fine to remove it if there is sufficient memory.

You can then use the pipeline to answer instructions:

Alternatively, if you prefer to not use trust_remote_code=True you can download instruct_pipeline.py, store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:

We present the results from various model benchmarks on the EleutherAI LLM Evaluation Harness for all models in the DLite family. Model results are sorted by mean score, ascending, to provide an ordering. These metrics serve to further show that none of the DLite models are state of the art, but rather further show that chat-like behaviors in LLMs can be trained almost independent of model size.

Detailed results can be found here