| model-index: | |
| - name: opt-350m | |
| results: | |
| - task: | |
| type: text-generation | |
| dataset: | |
| name: Wikitext | |
| type: wikitext | |
| metrics: | |
| - type: perplexity (BASELINE) | |
| value: 25.420656250994373 | |
| - type: perplexity (BASIC) | |
| value: 25.56288418958359 | |
| This is a d-Matrix functional reference of the OPT-350M model. | |
| The reference provides the following functional *configurations*: | |
| Configuration | Explanation | |
| :-- | :-- | |
| **`BASELINE`** | a reference functionally equivalent to the original model | |
| **`BASIC`** | all linear algebraic operands quantized to `MXINT8-64`, and all other operations transformed to approximated kernel simulations | |
| ### Usage | |
| Install d-Matrix [Dmx_Compressor](https://github.com/d-matrix-ai/dmx-compressor) first. | |
| ```sh | |
| pip install dmx_compressor | |
| ``` | |
| The following is an example model and its evaluation. | |
| ```sh | |
| pip install lm-eval | |
| ``` | |
| ```python | |
| from dmx.compressor.modeling import DmxModel | |
| import lm_eval | |
| model_args = f"pretrained="d-matrix/opt-350m",trust_remote_code=True" | |
| lm = lm_eval.api.registry.get_model("hf").create_from_arg_string(model_args, {"batch_size": 1}) | |
| # Transform the model with DMX | |
| lm._model = DmxModel.from_torch(lm._model).to_basic_model() # Using BASIC configuration | |
| eval_results = lm_eval.evaluate(lm, lm_eval.tasks.get_task_dict([task]) # Assign desired task, i.e. "wikitext" | |
| ``` |