Isabelle Cudlitz
commited on
Commit
·
96e71d3
1
Parent(s):
b60c33f
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3852,4 +3852,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3852 |
### Framework versions
|
| 3853 |
|
| 3854 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3855 |
- PEFT 0.6.2
|
|
|
|
| 3852 |
### Framework versions
|
| 3853 |
|
| 3854 |
|
| 3855 |
+
- PEFT 0.6.2
|
| 3856 |
+
## Training procedure
|
| 3857 |
+
|
| 3858 |
+
|
| 3859 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3860 |
+
- load_in_8bit: True
|
| 3861 |
+
- load_in_4bit: False
|
| 3862 |
+
- llm_int8_threshold: 6.0
|
| 3863 |
+
- llm_int8_skip_modules: None
|
| 3864 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3865 |
+
- llm_int8_has_fp16_weight: False
|
| 3866 |
+
- bnb_4bit_quant_type: fp4
|
| 3867 |
+
- bnb_4bit_use_double_quant: False
|
| 3868 |
+
- bnb_4bit_compute_dtype: float32
|
| 3869 |
+
|
| 3870 |
+
### Framework versions
|
| 3871 |
+
|
| 3872 |
+
|
| 3873 |
- 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 sha256:84c62a869378f1cae03b2e82ff9a6826d9e07d1e612081528c91068f8fddd8c4
|
| 3 |
size 21020682
|