Isabelle Cudlitz
commited on
Commit
·
934dc1a
1
Parent(s):
31539a2
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -594,4 +594,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 594 |
### Framework versions
|
| 595 |
|
| 596 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 597 |
- PEFT 0.6.2
|
|
|
|
| 594 |
### Framework versions
|
| 595 |
|
| 596 |
|
| 597 |
+
- PEFT 0.6.2
|
| 598 |
+
## Training procedure
|
| 599 |
+
|
| 600 |
+
|
| 601 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 602 |
+
- load_in_8bit: True
|
| 603 |
+
- load_in_4bit: False
|
| 604 |
+
- llm_int8_threshold: 6.0
|
| 605 |
+
- llm_int8_skip_modules: None
|
| 606 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 607 |
+
- llm_int8_has_fp16_weight: False
|
| 608 |
+
- bnb_4bit_quant_type: fp4
|
| 609 |
+
- bnb_4bit_use_double_quant: False
|
| 610 |
+
- bnb_4bit_compute_dtype: float32
|
| 611 |
+
|
| 612 |
+
### Framework versions
|
| 613 |
+
|
| 614 |
+
|
| 615 |
- 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 sha256:484046f30d2c4fed23c786cc0742ba865e2b3ccbceac26c659a4c5d83943b971
|
| 3 |
size 21020682
|