unaidedelf87777
commited on
Commit
•
4659e53
1
Parent(s):
b66724f
Update README.md
Browse files
README.md
CHANGED
@@ -3,4 +3,27 @@ license: apache-2.0
|
|
3 |
pipeline_tag: text-generation
|
4 |
---
|
5 |
|
6 |
-
![DALL·E 2023-10-11 16.30.48 - Photo of a dark forest with tall, ancient trees. Their branches and leaves form intricate patterns, revealing a portal of swirling magical energy in t.png](https://cdn-uploads.huggingface.co/production/uploads/643c81209f5d314db2de9743/FE8hhNKnRX8UOE5qXNkZD.png)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
pipeline_tag: text-generation
|
4 |
---
|
5 |
|
6 |
+
![DALL·E 2023-10-11 16.30.48 - Photo of a dark forest with tall, ancient trees. Their branches and leaves form intricate patterns, revealing a portal of swirling magical energy in t.png](https://cdn-uploads.huggingface.co/production/uploads/643c81209f5d314db2de9743/FE8hhNKnRX8UOE5qXNkZD.png)
|
7 |
+
|
8 |
+
# Overview
|
9 |
+
|
10 |
+
This model is a finetune of Mistral7b on cleaned data from WizardLM Evol Instruct v2 196k. most instances of RLHF were removed from the dataset, so this should be treated as a unscensored model although it is not fully unscensored.
|
11 |
+
|
12 |
+
# Benchmarks
|
13 |
+
|
14 |
+
Wizard Mistral was only finetuned on >200k rows of evol instruct multi turn data, however it achieves competetive results when evaluated. below is wizard mistrals benchmark scores compared to the most popular mistral7b finetunes.
|
15 |
+
|
16 |
+
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA |
|
17 |
+
|--------------------------------------------------|---------|-------|-----------|------|------------|
|
18 |
+
| unaidedelf87777/wizard-mistral-v0.1 | 64.18 | 61.77 | 83.51 | 63.99| 47.46 |
|
19 |
+
| Undi95/Mistral-11B-TestBench11 | **67.21**| **64.42**| 83.93 | 63.82| 56.68 |
|
20 |
+
| Undi95/Mistral-11B-TestBench9 | 67.13 | 64.08 | 84.24 | **64** | 56.19 |
|
21 |
+
| ehartford/dolphin-2.1-mistral-7b | 67.06 | 64.42 | 84.92 | 63.32| 55.56 |
|
22 |
+
| ehartford/dolphin-2.1-mistral-7b (Duplicate?) | 67 | 63.99 | 85 | 63.44| 55.57 |
|
23 |
+
| Undi95/Mistral-11B-TestBench10 | 66.99 | 64.25 | 84.24 | 63.9 | 55.57 |
|
24 |
+
| teknuim/CollectiveCognition-v1.1-Mistral-7B | 66.56 | 62.12 | 84.17 | 62.35| **57.62** |
|
25 |
+
| Weyaxi/SlimOpenOrca-Mistral-7B | 66.54 | 62.97 | 83.49 | 62.3 | 57.39 |
|
26 |
+
| teknuim/CollectiveCognition-v1-Mistral-7B | 66.28 | 62.37 | **85.5** | 62.76| 54.48 |
|
27 |
+
| ehartford/samantha-1-2-mistral-7b | 65.87 | 64.08 | 85.08 | 63.91| 50.4 |
|
28 |
+
| Open-Orca/Mistral-7B-SlimOrca | 65.85 | 62.54 | 83.86 | 62.77| 54.23 |
|
29 |
+
| Open-Orca/Mistral-7B-OpenOrca | 65.84 | 64.08 | 83.99 | 62.24| 53.05 |
|