Commit
•
db70820
1
Parent(s):
7dbbc8c
results
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ This is only experimental Model created by following instruction from the nice B
|
|
| 13 |
|
| 14 |
You can run this model using the following code:
|
| 15 |
|
| 16 |
-
```
|
| 17 |
# Format prompt
|
| 18 |
message = [
|
| 19 |
{"role": "system", "content": "You are a helpful assistant chatbot."},
|
|
@@ -46,3 +46,20 @@ print(sequences[0]['generated_text'])
|
|
| 46 |
# <|assistant|>
|
| 47 |
# A Large Language Model (LLM) is a type of deep learning model that processes large amounts of text or data to improve the accuracy of natural language processing tasks such as sentiment analysis, machine translation, and question answering. LLMs are trained using large datasets, which allow them to generalize better and have better performance compared to traditional machine learning models. They are capable of handling vast amounts of text and can learn complex relationships between words, phrases, and sentences, making them an essential tool for natural language processing.
|
| 48 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
You can run this model using the following code:
|
| 15 |
|
| 16 |
+
```python
|
| 17 |
# Format prompt
|
| 18 |
message = [
|
| 19 |
{"role": "system", "content": "You are a helpful assistant chatbot."},
|
|
|
|
| 46 |
# <|assistant|>
|
| 47 |
# A Large Language Model (LLM) is a type of deep learning model that processes large amounts of text or data to improve the accuracy of natural language processing tasks such as sentiment analysis, machine translation, and question answering. LLMs are trained using large datasets, which allow them to generalize better and have better performance compared to traditional machine learning models. They are capable of handling vast amounts of text and can learn complex relationships between words, phrases, and sentences, making them an essential tool for natural language processing.
|
| 48 |
```
|
| 49 |
+
|
| 50 |
+
Results on GPT4ALL benchmark:
|
| 51 |
+
|
| 52 |
+
| Tasks | Metric |Value | |Stderr|
|
| 53 |
+
|-------------|--------|-----:|---|-----:|
|
| 54 |
+
|arc_challenge|acc |0.3003|± |0.0134|
|
| 55 |
+
| |acc_norm|0.3276|± |0.0137|
|
| 56 |
+
|arc_easy |acc |0.6115|± |0.0100|
|
| 57 |
+
| |acc_norm|0.5354|± |0.0102|
|
| 58 |
+
|boolq |acc |0.6147|± |0.0085|
|
| 59 |
+
|hellaswag |acc |0.4633|± |0.0050|
|
| 60 |
+
| |acc_norm|0.6033|± |0.0049|
|
| 61 |
+
|openbookqa |acc |0.2480|± |0.0193|
|
| 62 |
+
| |acc_norm|0.3720|± |0.0216|
|
| 63 |
+
|piqa |acc |0.7470|± |0.0101|
|
| 64 |
+
| |acc_norm|0.7470|± |0.0101|
|
| 65 |
+
|winogrande |acc |0.6054|± |0.0137|
|