Update README.md
Browse files
README.md
CHANGED
|
@@ -6,25 +6,21 @@ language:
|
|
| 6 |
|
| 7 |
# RedPajama-Chat-INCITE-6.9B
|
| 8 |
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
> TLDR: RedPajama-Chat-INCITE-6.9B is a 6.9B parameter language model.
|
| 12 |
-
|
| 13 |
-
RedPajama-Chat-INCITE-6.9B is TODO.
|
| 14 |
|
| 15 |
## Model Details
|
| 16 |
- **Developed by**: Together Computer.
|
| 17 |
- **Model type**: Language Model
|
| 18 |
- **Language(s)**: English
|
| 19 |
- **License**: Apache 2.0
|
| 20 |
-
- **Model Description**: A 6.9B parameter
|
| 21 |
-
- **Resources for more information**: TODO.
|
| 22 |
|
| 23 |
# Quick Start
|
| 24 |
|
| 25 |
## GPU Inference
|
| 26 |
|
| 27 |
-
This requires a GPU with
|
| 28 |
```python
|
| 29 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 30 |
# init
|
|
@@ -40,7 +36,7 @@ print(output_str)
|
|
| 40 |
|
| 41 |
## GPU Inference in Int8
|
| 42 |
|
| 43 |
-
This requires a GPU with
|
| 44 |
|
| 45 |
```python
|
| 46 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
@@ -85,22 +81,17 @@ Excluded uses are described below.
|
|
| 85 |
|
| 86 |
### Misuse, Malicious Use, and Out-of-Scope Use
|
| 87 |
|
| 88 |
-
TODO:
|
| 89 |
-
The OpenChatKit community provides RedPajama-Chat-INCITE-6.9B as an open source tool for building chatbots.
|
| 90 |
-
The community is not responsible for any misuse, malicious use, or out-of-scope use of the model.
|
| 91 |
It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.
|
| 92 |
|
| 93 |
#### Out-of-Scope Use
|
| 94 |
|
| 95 |
-
|
| 96 |
-
RedPajama-Chat-INCITE-6.9B is designed for use in chatbot applications and may not perform well for other use cases outside of its intended scope.
|
| 97 |
For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society.
|
| 98 |
It is important to consider the limitations of the model and to only use it for its intended purpose.
|
| 99 |
|
| 100 |
#### Misuse and Malicious Use
|
| 101 |
|
| 102 |
-
|
| 103 |
-
RedPajama-Chat-INCITE-6.9B is designed for use in chatbot applications and should not be used for any other purpose.
|
| 104 |
Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the OpenChatKit community project.
|
| 105 |
|
| 106 |
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
|
|
@@ -117,8 +108,7 @@ Using the model to generate content that is cruel to individuals is a misuse of
|
|
| 117 |
|
| 118 |
## Limitations
|
| 119 |
|
| 120 |
-
|
| 121 |
-
RedPajama-Chat-INCITE-6.9B, like other language model-based chatbots, has limitations that should be taken into consideration.
|
| 122 |
For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data.
|
| 123 |
We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.
|
| 124 |
|
|
|
|
| 6 |
|
| 7 |
# RedPajama-Chat-INCITE-6.9B
|
| 8 |
|
| 9 |
+
RedPajama-Chat-INCITE-6.9B-v1, is a large transformer-based language model developed by Together Computer and trained on the RedPajama-Data-1T dataset.
|
| 10 |
+
It is further fine-tuned on OASST1 and Dolly2 to enhance chatting ability.
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
## Model Details
|
| 13 |
- **Developed by**: Together Computer.
|
| 14 |
- **Model type**: Language Model
|
| 15 |
- **Language(s)**: English
|
| 16 |
- **License**: Apache 2.0
|
| 17 |
+
- **Model Description**: A 6.9B parameter pretrained language model.
|
|
|
|
| 18 |
|
| 19 |
# Quick Start
|
| 20 |
|
| 21 |
## GPU Inference
|
| 22 |
|
| 23 |
+
This requires a GPU with 16GB memory.
|
| 24 |
```python
|
| 25 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 26 |
# init
|
|
|
|
| 36 |
|
| 37 |
## GPU Inference in Int8
|
| 38 |
|
| 39 |
+
This requires a GPU with 12GB memory.
|
| 40 |
|
| 41 |
```python
|
| 42 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
| 81 |
|
| 82 |
### Misuse, Malicious Use, and Out-of-Scope Use
|
| 83 |
|
|
|
|
|
|
|
|
|
|
| 84 |
It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.
|
| 85 |
|
| 86 |
#### Out-of-Scope Use
|
| 87 |
|
| 88 |
+
RedPajama-Chat-INCITE-6.9B is a language model and may not perform well for other use cases outside of its intended scope.
|
|
|
|
| 89 |
For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society.
|
| 90 |
It is important to consider the limitations of the model and to only use it for its intended purpose.
|
| 91 |
|
| 92 |
#### Misuse and Malicious Use
|
| 93 |
|
| 94 |
+
RedPajama-Chat-INCITE-6.9B is designed for language modeling.
|
|
|
|
| 95 |
Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the OpenChatKit community project.
|
| 96 |
|
| 97 |
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
|
|
|
|
| 108 |
|
| 109 |
## Limitations
|
| 110 |
|
| 111 |
+
RedPajama-Chat-INCITE-6.9B, like other language models, has limitations that should be taken into consideration.
|
|
|
|
| 112 |
For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data.
|
| 113 |
We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.
|
| 114 |
|