Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,112 @@
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: red
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# MidReal
|
| 11 |
+
|
| 12 |
+
We follow an extremely simple format to organize and manage our models aand data.
|
| 13 |
+
|
| 14 |
+
# Model
|
| 15 |
+
|
| 16 |
+
### Format
|
| 17 |
+
|
| 18 |
+
Repo should be named as `midreal/{model_function}_{train_method}_{train_technique}_{base_model}_{date}`
|
| 19 |
+
|
| 20 |
+
Model card should include ([example](https://huggingface.co/midreal/passage_sft_qlora_llama3_70b_0704)):
|
| 21 |
+
|
| 22 |
+
```
|
| 23 |
+
# Data
|
| 24 |
+
|
| 25 |
+
Dataset trained with
|
| 26 |
+
|
| 27 |
+
# Base
|
| 28 |
+
|
| 29 |
+
Base model trained on
|
| 30 |
+
|
| 31 |
+
# Template
|
| 32 |
+
|
| 33 |
+
Prompt/Response template of the model
|
| 34 |
+
|
| 35 |
+
# System
|
| 36 |
+
|
| 37 |
+
MidReal system version that's compatible with the model
|
| 38 |
+
|
| 39 |
+
# W&B
|
| 40 |
+
|
| 41 |
+
Tracking of the training procedure
|
| 42 |
+
|
| 43 |
+
# PIC
|
| 44 |
+
|
| 45 |
+
Person in charge
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
### Usage
|
| 49 |
+
|
| 50 |
+
Models could be uploaded with:
|
| 51 |
+
```
|
| 52 |
+
upload
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
and downloaded with:
|
| 56 |
+
```
|
| 57 |
+
download
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
and updated with:
|
| 61 |
+
```
|
| 62 |
+
update
|
| 63 |
+
```
|
| 64 |
+
|
| 65 |
+
# Dataset
|
| 66 |
+
|
| 67 |
+
### Format
|
| 68 |
+
|
| 69 |
+
Repo should be named as `midreal/{model_function}_{train_method}_{status}_{date}`
|
| 70 |
+
|
| 71 |
+
Dataset card should include ([example](https://huggingface.co/datasets/midreal/passage_sft_lmflow_0704)):
|
| 72 |
+
|
| 73 |
+
```
|
| 74 |
+
# Data Schema
|
| 75 |
+
|
| 76 |
+
The schema that the data elements should follow
|
| 77 |
+
|
| 78 |
+
# PIC
|
| 79 |
+
|
| 80 |
+
Person in charge
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
Other information about the dataset is also welcome.
|
| 84 |
+
|
| 85 |
+
### Status
|
| 86 |
+
|
| 87 |
+
The production of dataset should somehow follow a pipeline from `raw_data` to `story_data` to `openai` or `lmflow` format.
|
| 88 |
+
|
| 89 |
+
`raw_data` is any data in its original appearance.
|
| 90 |
+
|
| 91 |
+
`story_data` currently follow [data_schema_0718](https://huggingface.co/datasets/midreal/data_schema_0718).
|
| 92 |
+
|
| 93 |
+
`openai` refers to [OpenAI Fine-tuning data format](https://platform.openai.com/docs/guides/fine-tuning/example-format).
|
| 94 |
+
|
| 95 |
+
`lmflow` refers to [LMFlow data format](https://optimalscale.github.io/LMFlow/examples/DATASETS.html#data-format).
|
| 96 |
+
|
| 97 |
+
### Usage
|
| 98 |
+
|
| 99 |
+
Datasets could be uploaded with:
|
| 100 |
+
```
|
| 101 |
+
upload
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
and downloaded with:
|
| 105 |
+
```
|
| 106 |
+
download
|
| 107 |
+
```
|
| 108 |
+
|
| 109 |
+
and updated with:
|
| 110 |
+
```
|
| 111 |
+
update
|
| 112 |
+
```
|