Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
datasets:
|
| 4 |
- irds/codesearchnet
|
| 5 |
- giganticode/java-cmpx-v1
|
|
@@ -84,6 +84,10 @@ datasets:
|
|
| 84 |
- seyyedaliayati/solidity-dataset
|
| 85 |
- jkhedri/psychology-dataset
|
| 86 |
- KonradSzafer/stackoverflow_linux
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
language:
|
| 88 |
- en
|
| 89 |
- it
|
|
@@ -93,6 +97,9 @@ language:
|
|
| 93 |
- ru
|
| 94 |
- ro
|
| 95 |
- el
|
|
|
|
|
|
|
|
|
|
| 96 |
metrics:
|
| 97 |
- accuracy
|
| 98 |
- bertscore
|
|
@@ -100,6 +107,8 @@ metrics:
|
|
| 100 |
- code_eval
|
| 101 |
- character
|
| 102 |
- brier_score
|
|
|
|
|
|
|
| 103 |
tags:
|
| 104 |
- code
|
| 105 |
- text-generation-inference
|
|
@@ -126,7 +135,7 @@ Aiden is a factual language model from Hugging Face, trained on a massive datase
|
|
| 126 |
|
| 127 |
### Model Specifications
|
| 128 |
|
| 129 |
-
Aiden is a Transformer-based LLM with
|
| 130 |
|
| 131 |
* Books
|
| 132 |
* Code
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
datasets:
|
| 4 |
- irds/codesearchnet
|
| 5 |
- giganticode/java-cmpx-v1
|
|
|
|
| 84 |
- seyyedaliayati/solidity-dataset
|
| 85 |
- jkhedri/psychology-dataset
|
| 86 |
- KonradSzafer/stackoverflow_linux
|
| 87 |
+
- vikp/textbook_quality_programming
|
| 88 |
+
- rombodawg/LosslessMegaCodeTrainingV3_MINI
|
| 89 |
+
- BelleGroup/multiturn_chat_0.8M
|
| 90 |
+
- smangrul/code-chat-assistant-v1
|
| 91 |
language:
|
| 92 |
- en
|
| 93 |
- it
|
|
|
|
| 97 |
- ru
|
| 98 |
- ro
|
| 99 |
- el
|
| 100 |
+
- ja
|
| 101 |
+
- ch
|
| 102 |
+
- zh
|
| 103 |
metrics:
|
| 104 |
- accuracy
|
| 105 |
- bertscore
|
|
|
|
| 107 |
- code_eval
|
| 108 |
- character
|
| 109 |
- brier_score
|
| 110 |
+
- cer
|
| 111 |
+
- chrf
|
| 112 |
tags:
|
| 113 |
- code
|
| 114 |
- text-generation-inference
|
|
|
|
| 135 |
|
| 136 |
### Model Specifications
|
| 137 |
|
| 138 |
+
Aiden is a Transformer-based LLM with 175B parameters. It is trained on a massive dataset of text and code, including the following:
|
| 139 |
|
| 140 |
* Books
|
| 141 |
* Code
|