Isabelle Cudlitz
commited on
Commit
·
ed06531
1
Parent(s):
83f7a7a
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -738,4 +738,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 738 |
### Framework versions
|
| 739 |
|
| 740 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 741 |
- PEFT 0.6.2
|
|
|
|
| 738 |
### Framework versions
|
| 739 |
|
| 740 |
|
| 741 |
+
- PEFT 0.6.2
|
| 742 |
+
## Training procedure
|
| 743 |
+
|
| 744 |
+
|
| 745 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 746 |
+
- load_in_8bit: False
|
| 747 |
+
- load_in_4bit: True
|
| 748 |
+
- llm_int8_threshold: 6.0
|
| 749 |
+
- llm_int8_skip_modules: None
|
| 750 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 751 |
+
- llm_int8_has_fp16_weight: False
|
| 752 |
+
- bnb_4bit_quant_type: fp4
|
| 753 |
+
- bnb_4bit_use_double_quant: True
|
| 754 |
+
- bnb_4bit_compute_dtype: float32
|
| 755 |
+
|
| 756 |
+
### Framework versions
|
| 757 |
+
|
| 758 |
+
|
| 759 |
- 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:f17b8343f4b2507af8a098d116ddeeedc7e5f1064cca6ef64b5bd79bdb0b1596
|
| 3 |
size 21020682
|