Isabelle Cudlitz
commited on
Commit
·
e894f16
1
Parent(s):
fe84b39
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -612,4 +612,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 612 |
### Framework versions
|
| 613 |
|
| 614 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 615 |
- PEFT 0.6.2
|
|
|
|
| 612 |
### Framework versions
|
| 613 |
|
| 614 |
|
| 615 |
+
- PEFT 0.6.2
|
| 616 |
+
## Training procedure
|
| 617 |
+
|
| 618 |
+
|
| 619 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 620 |
+
- load_in_8bit: False
|
| 621 |
+
- load_in_4bit: True
|
| 622 |
+
- llm_int8_threshold: 6.0
|
| 623 |
+
- llm_int8_skip_modules: None
|
| 624 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 625 |
+
- llm_int8_has_fp16_weight: False
|
| 626 |
+
- bnb_4bit_quant_type: fp4
|
| 627 |
+
- bnb_4bit_use_double_quant: True
|
| 628 |
+
- bnb_4bit_compute_dtype: float32
|
| 629 |
+
|
| 630 |
+
### Framework versions
|
| 631 |
+
|
| 632 |
+
|
| 633 |
- 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 sha256:7cc73449e868b186c47664148ea1ad499f6f8c5e1165c9bdb5889aa87c03fdac
|
| 3 |
size 21020682
|