Isabelle Cudlitz
commited on
Commit
·
0194453
1
Parent(s):
7f1b8dd
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -864,4 +864,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 864 |
### Framework versions
|
| 865 |
|
| 866 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 867 |
- PEFT 0.6.2
|
|
|
|
| 864 |
### Framework versions
|
| 865 |
|
| 866 |
|
| 867 |
+
- PEFT 0.6.2
|
| 868 |
+
## Training procedure
|
| 869 |
+
|
| 870 |
+
|
| 871 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 872 |
+
- load_in_8bit: False
|
| 873 |
+
- load_in_4bit: True
|
| 874 |
+
- llm_int8_threshold: 6.0
|
| 875 |
+
- llm_int8_skip_modules: None
|
| 876 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 877 |
+
- llm_int8_has_fp16_weight: False
|
| 878 |
+
- bnb_4bit_quant_type: fp4
|
| 879 |
+
- bnb_4bit_use_double_quant: True
|
| 880 |
+
- bnb_4bit_compute_dtype: float32
|
| 881 |
+
|
| 882 |
+
### Framework versions
|
| 883 |
+
|
| 884 |
+
|
| 885 |
- 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 sha256:81b09c81b5857b7432c0aaa34bad6ca0d67fd3d03587bab0f3a916b560f53442
|
| 3 |
size 21020682
|