Isabelle Cudlitz
commited on
Commit
·
e26847c
1
Parent(s):
c1c249c
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1764,4 +1764,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1764 |
### Framework versions
|
| 1765 |
|
| 1766 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1767 |
- PEFT 0.6.2
|
|
|
|
| 1764 |
### Framework versions
|
| 1765 |
|
| 1766 |
|
| 1767 |
+
- PEFT 0.6.2
|
| 1768 |
+
## Training procedure
|
| 1769 |
+
|
| 1770 |
+
|
| 1771 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1772 |
+
- load_in_8bit: True
|
| 1773 |
+
- load_in_4bit: False
|
| 1774 |
+
- llm_int8_threshold: 6.0
|
| 1775 |
+
- llm_int8_skip_modules: None
|
| 1776 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1777 |
+
- llm_int8_has_fp16_weight: False
|
| 1778 |
+
- bnb_4bit_quant_type: fp4
|
| 1779 |
+
- bnb_4bit_use_double_quant: False
|
| 1780 |
+
- bnb_4bit_compute_dtype: float32
|
| 1781 |
+
|
| 1782 |
+
### Framework versions
|
| 1783 |
+
|
| 1784 |
+
|
| 1785 |
- PEFT 0.6.2
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21020682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a4d2085f10ffa3a116c8c6f3f5cf1e098d0ca0a99f72bb20f8fc1901fc080d
|
| 3 |
size 21020682
|