Isabelle Cudlitz commited on
Commit ·
6bffea3
1
Parent(s): 10fd7f2
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -666,4 +666,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 666 |
### Framework versions
|
| 667 |
|
| 668 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 669 |
- PEFT 0.6.2
|
|
|
|
| 666 |
### Framework versions
|
| 667 |
|
| 668 |
|
| 669 |
+
- PEFT 0.6.2
|
| 670 |
+
## Training procedure
|
| 671 |
+
|
| 672 |
+
|
| 673 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 674 |
+
- load_in_8bit: False
|
| 675 |
+
- load_in_4bit: True
|
| 676 |
+
- llm_int8_threshold: 6.0
|
| 677 |
+
- llm_int8_skip_modules: None
|
| 678 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 679 |
+
- llm_int8_has_fp16_weight: False
|
| 680 |
+
- bnb_4bit_quant_type: fp4
|
| 681 |
+
- bnb_4bit_use_double_quant: True
|
| 682 |
+
- bnb_4bit_compute_dtype: float32
|
| 683 |
+
|
| 684 |
+
### Framework versions
|
| 685 |
+
|
| 686 |
+
|
| 687 |
- 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:bcb70680133c34eb3d58b4f7387aabe0036938f984a0098838100905ef1e431e
|
| 3 |
size 21020682
|