Add transformers library name, pipeline tag and paper link
#3
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -2,7 +2,10 @@
|
|
| 2 |
license: other
|
| 3 |
license_name: license
|
| 4 |
license_link: LICENSE
|
|
|
|
|
|
|
| 5 |
---
|
|
|
|
| 6 |
<div align="center">
|
| 7 |
<h1>
|
| 8 |
Index-1.9B
|
|
@@ -12,7 +15,7 @@ license_link: LICENSE
|
|
| 12 |
## Model Introduction
|
| 13 |
|
| 14 |
We are excited to announce the release of a lightweight version from the Index series models: the Index-1.9B series.
|
| 15 |
-
|
| 16 |
- **Index-1.9B base (this repository's model)** : The base model, with 1.9 billion non-embedding parameters, pre-trained on a 2.8T corpus mainly in Chinese and English. It leads in multiple evaluation benchmarks compared to models of the same level.
|
| 17 |
- Index-1.9B pure : A control version of the base model with the same parameters and training strategy, but strictly filtered out all instruction-related data from the corpus to verify the impact of instructions on benchmarks.
|
| 18 |
- Index-1.9B chat: A dialogue model aligned with SFT and DPO based on the Index-1.9B base. We found that due to the introduction of a lot of internet community corpus in our pre-training, the model has significantly more interesting chatting capabilities.
|
|
@@ -43,6 +46,4 @@ The Index-1.9B shows excellent performance in general understanding evaluations,
|
|
| 43 |
|MPT-30B (report)|/|63.48|46.9|/|/|79.9|50.6|76.5|
|
| 44 |
|Falcon-40B (report)|/|68.18|55.4|/|/|83.6|54.5|79.2|
|
| 45 |
|
| 46 |
-
Evaluation code is based on [OpenCompass](https://github.com/open-compass/opencompass) with compatibility modifications. See the [evaluate](./evaluate/) folder for details.
|
| 47 |
-
|
| 48 |
-
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: license
|
| 4 |
license_link: LICENSE
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
---
|
| 8 |
+
|
| 9 |
<div align="center">
|
| 10 |
<h1>
|
| 11 |
Index-1.9B
|
|
|
|
| 15 |
## Model Introduction
|
| 16 |
|
| 17 |
We are excited to announce the release of a lightweight version from the Index series models: the Index-1.9B series.
|
| 18 |
+
The open-source Index-1.9B series is described in the [Index SLM Technical Report](https://huggingface.co/papers/2607.09885) and includes the following models:
|
| 19 |
- **Index-1.9B base (this repository's model)** : The base model, with 1.9 billion non-embedding parameters, pre-trained on a 2.8T corpus mainly in Chinese and English. It leads in multiple evaluation benchmarks compared to models of the same level.
|
| 20 |
- Index-1.9B pure : A control version of the base model with the same parameters and training strategy, but strictly filtered out all instruction-related data from the corpus to verify the impact of instructions on benchmarks.
|
| 21 |
- Index-1.9B chat: A dialogue model aligned with SFT and DPO based on the Index-1.9B base. We found that due to the introduction of a lot of internet community corpus in our pre-training, the model has significantly more interesting chatting capabilities.
|
|
|
|
| 46 |
|MPT-30B (report)|/|63.48|46.9|/|/|79.9|50.6|76.5|
|
| 47 |
|Falcon-40B (report)|/|68.18|55.4|/|/|83.6|54.5|79.2|
|
| 48 |
|
| 49 |
+
Evaluation code is based on [OpenCompass](https://github.com/open-compass/opencompass) with compatibility modifications. See the [evaluate](./evaluate/) folder for details.
|
|
|
|
|
|