Update README.md
Browse files
README.md
CHANGED
|
@@ -10,10 +10,19 @@ Official research release for the family of **XGen** models (`7B`) by Salesforce
|
|
| 10 |
|
| 11 |
## Models
|
| 12 |
|
|
|
|
| 13 |
* [XGen-7B-4K-Base](https://huggingface.co/Salesforce/xgen-7b-4k-base): XGen-7B model pre-trained under 4K sequence length.
|
| 14 |
* License: Apache-2.0
|
| 15 |
* [XGen-7B-8K-Base](https://huggingface.co/Salesforce/xgen-7b-8k-base): XGen-7B model pre-trained under 8K sequence length.
|
| 16 |
* License: Apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
The training data for the models are tokenized with OpenAI Tiktoken library.
|
| 19 |
To use this model, install the package via `pip`:
|
|
|
|
| 10 |
|
| 11 |
## Models
|
| 12 |
|
| 13 |
+
### Base models
|
| 14 |
* [XGen-7B-4K-Base](https://huggingface.co/Salesforce/xgen-7b-4k-base): XGen-7B model pre-trained under 4K sequence length.
|
| 15 |
* License: Apache-2.0
|
| 16 |
* [XGen-7B-8K-Base](https://huggingface.co/Salesforce/xgen-7b-8k-base): XGen-7B model pre-trained under 8K sequence length.
|
| 17 |
* License: Apache-2.0
|
| 18 |
+
|
| 19 |
+
### Instruction-finetuned models
|
| 20 |
+
|
| 21 |
+
Supervised finetuned model on public domain instructional data. Released for ***research purpose*** only.
|
| 22 |
+
|
| 23 |
+
* [XGen-7B-8K-Inst](https://huggingface.co/Salesforce/xgen-7b-8k-inst)
|
| 24 |
+
|
| 25 |
+
## How to run
|
| 26 |
|
| 27 |
The training data for the models are tokenized with OpenAI Tiktoken library.
|
| 28 |
To use this model, install the package via `pip`:
|