README.md

---
model-index:
- name: Mistral-7B-v0.1
  results:
  - task:
      type: text-generation
    dataset:
      name: Wikitext
      type: wikitext
    metrics:
    - type: perplexity (BASELINE)
      value: 8.041976819283537
    - type: perplexity (BASIC)
      value: 221.02403769073769
---
This is a d-Matrix functional reference of the MISTRAL-7B-V0.1 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
git clone https://github.com/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .
```

```python
from dmx.compressor.modeling import DmxModel
import lm_eval

model_args = "pretrained='d-matrix/Mistral',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"
```