Isabelle Cudlitz
commited on
Commit
·
f19375c
1
Parent(s):
6bffea3
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -684,4 +684,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 684 |
### Framework versions
|
| 685 |
|
| 686 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 687 |
- PEFT 0.6.2
|
|
|
|
| 684 |
### Framework versions
|
| 685 |
|
| 686 |
|
| 687 |
+
- PEFT 0.6.2
|
| 688 |
+
## Training procedure
|
| 689 |
+
|
| 690 |
+
|
| 691 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 692 |
+
- load_in_8bit: False
|
| 693 |
+
- load_in_4bit: True
|
| 694 |
+
- llm_int8_threshold: 6.0
|
| 695 |
+
- llm_int8_skip_modules: None
|
| 696 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 697 |
+
- llm_int8_has_fp16_weight: False
|
| 698 |
+
- bnb_4bit_quant_type: fp4
|
| 699 |
+
- bnb_4bit_use_double_quant: True
|
| 700 |
+
- bnb_4bit_compute_dtype: float32
|
| 701 |
+
|
| 702 |
+
### Framework versions
|
| 703 |
+
|
| 704 |
+
|
| 705 |
- 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 sha256:675a361a0e66e6901686a9b33b69989a9653973a0b77483975328cc496ea8787
|
| 3 |
size 21020682
|