Update read.me
Browse files
README.md
CHANGED
|
@@ -1,5 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
Trained on [mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset.
|
|
@@ -62,4 +71,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 62 |
| TruthfulQA (0-shot) | 46.08 |
|
| 63 |
| Winogrande (5-shot) | 76.8 |
|
| 64 |
| GSM8K (5-shot) | 16.0 |
|
| 65 |
-
| DROP (3-shot) | 11.22 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
- es
|
| 7 |
+
base_model:
|
| 8 |
+
- Qwen/Qwen3-Next-80B-A3B-Instruct
|
| 9 |
+
library_name: adapter-transformers
|
| 10 |
+
tags:
|
| 11 |
+
- agent
|
| 12 |
---
|
| 13 |
|
| 14 |
Trained on [mistral-7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset.
|
|
|
|
| 71 |
| TruthfulQA (0-shot) | 46.08 |
|
| 72 |
| Winogrande (5-shot) | 76.8 |
|
| 73 |
| GSM8K (5-shot) | 16.0 |
|
| 74 |
+
| DROP (3-shot) | 11.22 |
|