Isabelle Cudlitz
commited on
Commit
·
ca681e7
1
Parent(s):
66b0dbe
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1908,4 +1908,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1908 |
### Framework versions
|
| 1909 |
|
| 1910 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1911 |
- PEFT 0.6.2
|
|
|
|
| 1908 |
### Framework versions
|
| 1909 |
|
| 1910 |
|
| 1911 |
+
- PEFT 0.6.2
|
| 1912 |
+
## Training procedure
|
| 1913 |
+
|
| 1914 |
+
|
| 1915 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1916 |
+
- load_in_8bit: True
|
| 1917 |
+
- load_in_4bit: False
|
| 1918 |
+
- llm_int8_threshold: 6.0
|
| 1919 |
+
- llm_int8_skip_modules: None
|
| 1920 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1921 |
+
- llm_int8_has_fp16_weight: False
|
| 1922 |
+
- bnb_4bit_quant_type: fp4
|
| 1923 |
+
- bnb_4bit_use_double_quant: False
|
| 1924 |
+
- bnb_4bit_compute_dtype: float32
|
| 1925 |
+
|
| 1926 |
+
### Framework versions
|
| 1927 |
+
|
| 1928 |
+
|
| 1929 |
- 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 sha256:97974a97e4033e1df0b703d53d2d9a1a2b208ece89ee17564e3bec89c42fb03b
|
| 3 |
size 21020682
|