Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,8 @@ pipeline_tag: image-text-to-text
|
|
| 10 |
---
|
| 11 |
|
| 12 |
## Model Overview
|
| 13 |
-
This model
|
| 14 |
-
|
| 15 |
**Fine-tuning Framework:** Finetuned using Unsloth optimized LoRA adapters.
|
| 16 |
|
| 17 |
---
|
|
@@ -20,7 +20,7 @@ It was trained on the **Feedback-Collection** dataset from the *Prometheus Eval*
|
|
| 20 |
|
| 21 |
| Model | Benchmark | Pearson r | Spearman Ο |
|
| 22 |
|:------|:-----------|:----------:|:------------:|
|
| 23 |
-
| π© **
|
| 24 |
| π¨ **Prometheus 2 (8Γ7B)** *(Kim et al., 2024)* | Feedback Bench / Preference Bench | β 0.898 / β | β 0.90 / β |
|
| 25 |
|
| 26 |
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
## Model Overview
|
| 13 |
+
This model is a fine-tuned version of the `unsloth/gemma-3-4b-it`
|
| 14 |
+
trained on the **Feedback-Collection** dataset from the *Prometheus Eval*.
|
| 15 |
**Fine-tuning Framework:** Finetuned using Unsloth optimized LoRA adapters.
|
| 16 |
|
| 17 |
---
|
|
|
|
| 20 |
|
| 21 |
| Model | Benchmark | Pearson r | Spearman Ο |
|
| 22 |
|:------|:-----------|:----------:|:------------:|
|
| 23 |
+
| π© **This model** | Feedback Bench | **0.9198** | **0.9210** |
|
| 24 |
| π¨ **Prometheus 2 (8Γ7B)** *(Kim et al., 2024)* | Feedback Bench / Preference Bench | β 0.898 / β | β 0.90 / β |
|
| 25 |
|
| 26 |
|