Isabelle Cudlitz
commited on
Commit
·
b60c33f
1
Parent(s):
335c9a5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3834,4 +3834,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3834 |
### Framework versions
|
| 3835 |
|
| 3836 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3837 |
- PEFT 0.6.2
|
|
|
|
| 3834 |
### Framework versions
|
| 3835 |
|
| 3836 |
|
| 3837 |
+
- PEFT 0.6.2
|
| 3838 |
+
## Training procedure
|
| 3839 |
+
|
| 3840 |
+
|
| 3841 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3842 |
+
- load_in_8bit: True
|
| 3843 |
+
- load_in_4bit: False
|
| 3844 |
+
- llm_int8_threshold: 6.0
|
| 3845 |
+
- llm_int8_skip_modules: None
|
| 3846 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3847 |
+
- llm_int8_has_fp16_weight: False
|
| 3848 |
+
- bnb_4bit_quant_type: fp4
|
| 3849 |
+
- bnb_4bit_use_double_quant: False
|
| 3850 |
+
- bnb_4bit_compute_dtype: float32
|
| 3851 |
+
|
| 3852 |
+
### Framework versions
|
| 3853 |
+
|
| 3854 |
+
|
| 3855 |
- 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 sha256:0c99afa163b051d5056e5700a04d135ebae4f41f95872ec8d9a6f8b1dacdb7c1
|
| 3 |
size 21020682
|