Commit
·
f881940
1
Parent(s):
947920f
Create README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- ehartford/dolphin
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
**Base Model :** manojpreveen/mpt-30b-v4
|
| 8 |
+
|
| 9 |
+
**Tool :** MosaicML's llm-foundry (https://github.com/mosaicml/llm-foundry)
|
| 10 |
+
|
| 11 |
+
**Dataset :** Entire flan1m-GPT4 dataset
|
| 12 |
+
|
| 13 |
+
**Config yaml with Model Params :** https://huggingface.co/manojpreveen/mpt-30b-v5/blob/main/mpt-30b_v5.yaml
|
| 14 |
+
|
| 15 |
+
***Description :*** **mosaicml/mpt-30b** -> Finetuning on (Entire flan3m-GPT3.5 dataset for 4 epochs) **manojpreveen/mpt-30b-v4** -> Finetuning on (Entire flan1m-GPT4 dataset for 1 epoch) -> **manojpreveen/mpt-30b-v5**
|
| 16 |
+
|
| 17 |
+
**Prompt Format :**
|
| 18 |
+
|
| 19 |
+
```
|
| 20 |
+
<system>: [system prompt]
|
| 21 |
+
|
| 22 |
+
<human>: [question]
|
| 23 |
+
|
| 24 |
+
<bot>:
|
| 25 |
+
```
|