Isabelle Cudlitz
commited on
Commit
·
08f90f9
1
Parent(s):
c076243
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -774,4 +774,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 774 |
### Framework versions
|
| 775 |
|
| 776 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 777 |
- PEFT 0.6.2
|
|
|
|
| 774 |
### Framework versions
|
| 775 |
|
| 776 |
|
| 777 |
+
- PEFT 0.6.2
|
| 778 |
+
## Training procedure
|
| 779 |
+
|
| 780 |
+
|
| 781 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 782 |
+
- load_in_8bit: True
|
| 783 |
+
- load_in_4bit: False
|
| 784 |
+
- llm_int8_threshold: 6.0
|
| 785 |
+
- llm_int8_skip_modules: None
|
| 786 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 787 |
+
- llm_int8_has_fp16_weight: False
|
| 788 |
+
- bnb_4bit_quant_type: fp4
|
| 789 |
+
- bnb_4bit_use_double_quant: False
|
| 790 |
+
- bnb_4bit_compute_dtype: float32
|
| 791 |
+
|
| 792 |
+
### Framework versions
|
| 793 |
+
|
| 794 |
+
|
| 795 |
- 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 sha256:6775435f698f9e3e2eeae6f1f524399dfef5aabcdff84ff44ec1dc127f7be427
|
| 3 |
size 21020682
|