Isabelle Cudlitz
commited on
Commit
·
8302d48
1
Parent(s):
14cc589
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2772,4 +2772,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2772 |
### Framework versions
|
| 2773 |
|
| 2774 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2775 |
- PEFT 0.6.2
|
|
|
|
| 2772 |
### Framework versions
|
| 2773 |
|
| 2774 |
|
| 2775 |
+
- PEFT 0.6.2
|
| 2776 |
+
## Training procedure
|
| 2777 |
+
|
| 2778 |
+
|
| 2779 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2780 |
+
- load_in_8bit: True
|
| 2781 |
+
- load_in_4bit: False
|
| 2782 |
+
- llm_int8_threshold: 6.0
|
| 2783 |
+
- llm_int8_skip_modules: None
|
| 2784 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2785 |
+
- llm_int8_has_fp16_weight: False
|
| 2786 |
+
- bnb_4bit_quant_type: fp4
|
| 2787 |
+
- bnb_4bit_use_double_quant: False
|
| 2788 |
+
- bnb_4bit_compute_dtype: float32
|
| 2789 |
+
|
| 2790 |
+
### Framework versions
|
| 2791 |
+
|
| 2792 |
+
|
| 2793 |
- 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:f2c05c0cf1dfa72833f67c629761a95d458667c209f0d9af8413fce3a6f3a373
|
| 3 |
size 21020682
|