Isabelle Cudlitz
commited on
Commit
·
4db125b
1
Parent(s):
9c68675
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2808,4 +2808,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2808 |
### Framework versions
|
| 2809 |
|
| 2810 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2811 |
- PEFT 0.6.2
|
|
|
|
| 2808 |
### Framework versions
|
| 2809 |
|
| 2810 |
|
| 2811 |
+
- PEFT 0.6.2
|
| 2812 |
+
## Training procedure
|
| 2813 |
+
|
| 2814 |
+
|
| 2815 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2816 |
+
- load_in_8bit: True
|
| 2817 |
+
- load_in_4bit: False
|
| 2818 |
+
- llm_int8_threshold: 6.0
|
| 2819 |
+
- llm_int8_skip_modules: None
|
| 2820 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2821 |
+
- llm_int8_has_fp16_weight: False
|
| 2822 |
+
- bnb_4bit_quant_type: fp4
|
| 2823 |
+
- bnb_4bit_use_double_quant: False
|
| 2824 |
+
- bnb_4bit_compute_dtype: float32
|
| 2825 |
+
|
| 2826 |
+
### Framework versions
|
| 2827 |
+
|
| 2828 |
+
|
| 2829 |
- 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 sha256:8db0dfbbcc96cfe7251d148279b533e1692bb0435c5da69e7adf885e2b1b3d54
|
| 3 |
size 21020682
|