Isabelle Cudlitz
commited on
Commit
·
66a13ef
1
Parent(s):
96e71d3
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3870,4 +3870,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3870 |
### Framework versions
|
| 3871 |
|
| 3872 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3873 |
- PEFT 0.6.2
|
|
|
|
| 3870 |
### Framework versions
|
| 3871 |
|
| 3872 |
|
| 3873 |
+
- PEFT 0.6.2
|
| 3874 |
+
## Training procedure
|
| 3875 |
+
|
| 3876 |
+
|
| 3877 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3878 |
+
- load_in_8bit: True
|
| 3879 |
+
- load_in_4bit: False
|
| 3880 |
+
- llm_int8_threshold: 6.0
|
| 3881 |
+
- llm_int8_skip_modules: None
|
| 3882 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3883 |
+
- llm_int8_has_fp16_weight: False
|
| 3884 |
+
- bnb_4bit_quant_type: fp4
|
| 3885 |
+
- bnb_4bit_use_double_quant: False
|
| 3886 |
+
- bnb_4bit_compute_dtype: float32
|
| 3887 |
+
|
| 3888 |
+
### Framework versions
|
| 3889 |
+
|
| 3890 |
+
|
| 3891 |
- 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 sha256:2d2ef40656153ecb9b8cb132be8d4eeb8f03043a27675b355ec153ded3fd940d
|
| 3 |
size 21020682
|