Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Salesforce/wikitext
|
| 5 |
+
- VisionTheta/fineweb-1B
|
| 6 |
+
- Voxel51/fiftyone-qa-pairs-14k
|
| 7 |
+
- Open-Orca/OpenOrca
|
| 8 |
+
- OpenAssistant/oasst2
|
| 9 |
+
- Ereeeeef3/Qu-QA-v2
|
| 10 |
+
- tau/commonsense_qa
|
| 11 |
+
- OpenAssistant/oasst1
|
| 12 |
+
- hkust-nlp/deita-10k-v0
|
| 13 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
| 14 |
+
- meta-math/MetaMathQA
|
| 15 |
+
- HuggingFaceH4/ultrachat_200k
|
| 16 |
+
language:
|
| 17 |
+
- en
|
| 18 |
+
pipeline_tag: text-generation
|
| 19 |
+
---
|
| 20 |
+
# Cascade0 170M Base Model
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
Base model of the entire Cascade0-159M-DPO-Instruct and Normal Instruct saga.
|
| 25 |
+
#### Max context size is 1512.
|
| 26 |
+
## Cascade0 Base VS other small models
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
made with LMEval Harness
|
| 32 |
+
|