Isabelle Cudlitz
commited on
Commit
·
dd3b4bf
1
Parent(s):
cd015f3
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1872,4 +1872,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1872 |
### Framework versions
|
| 1873 |
|
| 1874 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1875 |
- PEFT 0.6.2
|
|
|
|
| 1872 |
### Framework versions
|
| 1873 |
|
| 1874 |
|
| 1875 |
+
- PEFT 0.6.2
|
| 1876 |
+
## Training procedure
|
| 1877 |
+
|
| 1878 |
+
|
| 1879 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1880 |
+
- load_in_8bit: True
|
| 1881 |
+
- load_in_4bit: False
|
| 1882 |
+
- llm_int8_threshold: 6.0
|
| 1883 |
+
- llm_int8_skip_modules: None
|
| 1884 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1885 |
+
- llm_int8_has_fp16_weight: False
|
| 1886 |
+
- bnb_4bit_quant_type: fp4
|
| 1887 |
+
- bnb_4bit_use_double_quant: False
|
| 1888 |
+
- bnb_4bit_compute_dtype: float32
|
| 1889 |
+
|
| 1890 |
+
### Framework versions
|
| 1891 |
+
|
| 1892 |
+
|
| 1893 |
- 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 sha256:8cc7a34964091ab3073799f650d43f9664d93d6860bf0c2dc33cd0d5807c583d
|
| 3 |
size 21020682
|