sam-mosaic
commited on
Commit
•
bab6ea0
1
Parent(s):
2d7b13f
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
datasets:
|
4 |
- competition_math
|
5 |
- knkarthick/dialogsum
|
@@ -20,7 +20,7 @@ inference: false
|
|
20 |
MPT-7B-Instruct-8k is a model for long-form instruction following, especially question-answering on and summarization of longer documents.
|
21 |
It is built by finetuning [MPT-7B-8k](https://huggingface.co/mosaicml/mpt-7b-8k) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
|
22 |
This is the same dataset that [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct) was trained on.
|
23 |
-
* License:
|
24 |
|
25 |
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
|
26 |
|
@@ -30,7 +30,7 @@ July 18, 2023
|
|
30 |
|
31 |
## Model License
|
32 |
|
33 |
-
|
34 |
|
35 |
## Documentation
|
36 |
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
datasets:
|
4 |
- competition_math
|
5 |
- knkarthick/dialogsum
|
|
|
20 |
MPT-7B-Instruct-8k is a model for long-form instruction following, especially question-answering on and summarization of longer documents.
|
21 |
It is built by finetuning [MPT-7B-8k](https://huggingface.co/mosaicml/mpt-7b-8k) on [Dolly HHRLHF](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets. It is also trained on [Competition Math](https://huggingface.co/datasets/competition_math), [Duorc](https://huggingface.co/datasets/duorc), [CoT GSM8k](https://huggingface.co/datasets/conceptofmind/cot_submix_original), [Qasper](https://huggingface.co/datasets/allenai/qasper), [Quality](https://huggingface.co/datasets/emozilla/quality), [Summ Screen FD](https://huggingface.co/datasets/tau/scrolls) and [Spider](https://huggingface.co/datasets/spider).
|
22 |
This is the same dataset that [MPT-30B-Instruct](https://huggingface.co/mosaicml/mpt-30b-instruct) was trained on.
|
23 |
+
* License: Apache 2.0
|
24 |
|
25 |
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
|
26 |
|
|
|
30 |
|
31 |
## Model License
|
32 |
|
33 |
+
Apache 2.0
|
34 |
|
35 |
## Documentation
|
36 |
|