xmadai
/

Mistral-Small-Instruct-2409-xMADai-INT4

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

JonahYixMAD commited on Oct 21, 2024

Commit

006e173

·

verified ·

1 Parent(s): 69bbf22

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ This repository contains [`mistralai/Mistral-Small-Instruct-2409`](https://huggi
 2. **Accuracy:** This xMADified model preserves the quality of the full-precision model. In the table below, we present the zero-shot accuracy on popular benchmarks of this xMADified model against the [GPTQ](https://github.com/AutoGPTQ/AutoGPTQ)-quantized model (both w4g128 for a fair comparison). GPTQ fails on the difficult **MMLU** task, while the xMADai model offers significantly higher accuracy.
-| Benchmark | xMADai Mistral-Small-Instruct-2409 (compared to GPTQ Mistral-Small-Instruct-2409) |
 |---|---|
 | **MMLU** | 49.45 → **68.59** |
 | **Arc Challenge** | 56.14 → **57.51** |

 2. **Accuracy:** This xMADified model preserves the quality of the full-precision model. In the table below, we present the zero-shot accuracy on popular benchmarks of this xMADified model against the [GPTQ](https://github.com/AutoGPTQ/AutoGPTQ)-quantized model (both w4g128 for a fair comparison). GPTQ fails on the difficult **MMLU** task, while the xMADai model offers significantly higher accuracy.
+| Benchmark | xMADai Mistral-Small-Instruct-2409<br>(compared to GPTQ Mistral-Small-Instruct-2409) |
 |---|---|
 | **MMLU** | 49.45 → **68.59** |
 | **Arc Challenge** | 56.14 → **57.51** |