Isabelle Cudlitz
commited on
Commit
·
01c892a
1
Parent(s):
4e79227
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3654,4 +3654,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3654 |
### Framework versions
|
| 3655 |
|
| 3656 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3657 |
- PEFT 0.6.2
|
|
|
|
| 3654 |
### Framework versions
|
| 3655 |
|
| 3656 |
|
| 3657 |
+
- PEFT 0.6.2
|
| 3658 |
+
## Training procedure
|
| 3659 |
+
|
| 3660 |
+
|
| 3661 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3662 |
+
- load_in_8bit: True
|
| 3663 |
+
- load_in_4bit: False
|
| 3664 |
+
- llm_int8_threshold: 6.0
|
| 3665 |
+
- llm_int8_skip_modules: None
|
| 3666 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3667 |
+
- llm_int8_has_fp16_weight: False
|
| 3668 |
+
- bnb_4bit_quant_type: fp4
|
| 3669 |
+
- bnb_4bit_use_double_quant: False
|
| 3670 |
+
- bnb_4bit_compute_dtype: float32
|
| 3671 |
+
|
| 3672 |
+
### Framework versions
|
| 3673 |
+
|
| 3674 |
+
|
| 3675 |
- 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 sha256:76c2ad8e5160e0df39cd5344c1cf8df0b44be2e5f2c4155a87c5b07a3b57a968
|
| 3 |
size 21020682
|