Isabelle Cudlitz
commited on
Commit
·
9565d20
1
Parent(s):
6690d2d
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3780,4 +3780,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3780 |
### Framework versions
|
| 3781 |
|
| 3782 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3783 |
- PEFT 0.6.2
|
|
|
|
| 3780 |
### Framework versions
|
| 3781 |
|
| 3782 |
|
| 3783 |
+
- PEFT 0.6.2
|
| 3784 |
+
## Training procedure
|
| 3785 |
+
|
| 3786 |
+
|
| 3787 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3788 |
+
- load_in_8bit: True
|
| 3789 |
+
- load_in_4bit: False
|
| 3790 |
+
- llm_int8_threshold: 6.0
|
| 3791 |
+
- llm_int8_skip_modules: None
|
| 3792 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3793 |
+
- llm_int8_has_fp16_weight: False
|
| 3794 |
+
- bnb_4bit_quant_type: fp4
|
| 3795 |
+
- bnb_4bit_use_double_quant: False
|
| 3796 |
+
- bnb_4bit_compute_dtype: float32
|
| 3797 |
+
|
| 3798 |
+
### Framework versions
|
| 3799 |
+
|
| 3800 |
+
|
| 3801 |
- 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:ab7b9beb8327a078b48b7536d62e1c577f4908a716aaf04ed1d5a91a54445026
|
| 3 |
size 21020682
|