Upload model
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
---
|
|
@@ -27,8 +41,9 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 27 |
- bnb_4bit_quant_type: fp4
|
| 28 |
- bnb_4bit_use_double_quant: False
|
| 29 |
- bnb_4bit_compute_dtype: float32
|
|
|
|
|
|
|
| 30 |
### Framework versions
|
| 31 |
|
| 32 |
- PEFT 0.6.0.dev0
|
| 33 |
-
|
| 34 |
- PEFT 0.6.0.dev0
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
`facebook/xglm-7.5B` lora fine tune with `Thaweewat/alpaca-cleaned-52k-th`
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
template
|
| 9 |
+
```
|
| 10 |
+
### Question: instruction
|
| 11 |
+
input
|
| 12 |
+
### Answer:
|
| 13 |
+
```
|
| 14 |
+
|
| 15 |
---
|
| 16 |
library_name: peft
|
| 17 |
---
|
|
|
|
| 41 |
- bnb_4bit_quant_type: fp4
|
| 42 |
- bnb_4bit_use_double_quant: False
|
| 43 |
- bnb_4bit_compute_dtype: float32
|
| 44 |
+
|
| 45 |
+
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- PEFT 0.6.0.dev0
|
|
|
|
| 49 |
- PEFT 0.6.0.dev0
|