---
model-index:
- name: bloom-7b1
  results:
  - task:
      type: text-generation
    dataset:
      name: Wikitext
      type: wikitext
    metrics:
    - type: perplexity (BASELINE)
      value: 14.730414494391944
    - type: perplexity (BASIC)
      value: 14.811252297039884
---
This is a d-Matrix functional reference of the BLOOM-7B1 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/bloom-7b1",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"
```