empirischtech
/

DeepSeek-R1-Distill-Llama-70B-gptq-4bit

Text Generation

4-bit precision

Model card Files Files and versions Community

rwmasood commited on Feb 5

Commit

a87aa26

·

verified ·

1 Parent(s): 98a1b61

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -20,12 +20,12 @@ This document presents the evaluation results of `DeepSeek-R1-Distill-Llama-70B`
 ## 📊 Evaluation Summary
-| **Metric**            | **Value**  | **Description**  |
-|----------------------|-----------|-----------------|
-| **Accuracy (acc,none)** | `21.2%`  | Raw accuracy - percentage of correct answers. |
-| **Standard Error (acc_stderr,none)** | `1.19%` | Uncertainty in the accuracy estimate. |
-| **Normalized Accuracy (acc_norm,none)** | `25.4%`  | Accuracy after dataset-specific normalization. |
-| **Standard Error (acc_norm_stderr,none)** | `1.27%` | Uncertainty for normalized accuracy. |
 📌 **Interpretation:**
 - The model correctly answered **21.2% of the questions**.

 ## 📊 Evaluation Summary
+| **Metric**            | **Value**  | **Description**  | **8bit-version*  |
+|----------------------|-----------|-----------------|-----------|
+| **Accuracy (acc,none)** | `21.2%`  | Raw accuracy - percentage of correct answers. | `21.2%`  |
+| **Standard Error (acc_stderr,none)** | `1.19%` | Uncertainty in the accuracy estimate. | `1.2%`  |
+| **Normalized Accuracy (acc_norm,none)** | `25.4%`  | Accuracy after dataset-specific normalization. | `25.2%`  |
+| **Standard Error (acc_norm_stderr,none)** | `1.27%` | Uncertainty for normalized accuracy. | `1.3%`  |
 📌 **Interpretation:**
 - The model correctly answered **21.2% of the questions**.