Isabelle Cudlitz
commited on
Commit
·
38f0bda
1
Parent(s):
f19375c
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -702,4 +702,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 702 |
### Framework versions
|
| 703 |
|
| 704 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 705 |
- PEFT 0.6.2
|
|
|
|
| 702 |
### Framework versions
|
| 703 |
|
| 704 |
|
| 705 |
+
- PEFT 0.6.2
|
| 706 |
+
## Training procedure
|
| 707 |
+
|
| 708 |
+
|
| 709 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 710 |
+
- load_in_8bit: False
|
| 711 |
+
- load_in_4bit: True
|
| 712 |
+
- llm_int8_threshold: 6.0
|
| 713 |
+
- llm_int8_skip_modules: None
|
| 714 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 715 |
+
- llm_int8_has_fp16_weight: False
|
| 716 |
+
- bnb_4bit_quant_type: fp4
|
| 717 |
+
- bnb_4bit_use_double_quant: True
|
| 718 |
+
- bnb_4bit_compute_dtype: float32
|
| 719 |
+
|
| 720 |
+
### Framework versions
|
| 721 |
+
|
| 722 |
+
|
| 723 |
- 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 sha256:22d7393c44c82ce7a81335154eb50a20fb12aa0f7466b42711d42221d1ac768f
|
| 3 |
size 21020682
|