Isabelle Cudlitz
commited on
Commit
·
690e9e2
1
Parent(s):
f286818
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3906,4 +3906,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3906 |
### Framework versions
|
| 3907 |
|
| 3908 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3909 |
- PEFT 0.6.2
|
|
|
|
| 3906 |
### Framework versions
|
| 3907 |
|
| 3908 |
|
| 3909 |
+
- PEFT 0.6.2
|
| 3910 |
+
## Training procedure
|
| 3911 |
+
|
| 3912 |
+
|
| 3913 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3914 |
+
- load_in_8bit: True
|
| 3915 |
+
- load_in_4bit: False
|
| 3916 |
+
- llm_int8_threshold: 6.0
|
| 3917 |
+
- llm_int8_skip_modules: None
|
| 3918 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3919 |
+
- llm_int8_has_fp16_weight: False
|
| 3920 |
+
- bnb_4bit_quant_type: fp4
|
| 3921 |
+
- bnb_4bit_use_double_quant: False
|
| 3922 |
+
- bnb_4bit_compute_dtype: float32
|
| 3923 |
+
|
| 3924 |
+
### Framework versions
|
| 3925 |
+
|
| 3926 |
+
|
| 3927 |
- 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:ae2a1868d89e2fc439b7ab90d073e4d7edc5026873e4f5f44a0e25470002b8da
|
| 3 |
size 21020682
|