Isabelle Cudlitz
commited on
Commit
·
e4cc87f
1
Parent(s):
cce8b1f
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -918,4 +918,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 918 |
### Framework versions
|
| 919 |
|
| 920 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 921 |
- PEFT 0.6.2
|
|
|
|
| 918 |
### Framework versions
|
| 919 |
|
| 920 |
|
| 921 |
+
- PEFT 0.6.2
|
| 922 |
+
## Training procedure
|
| 923 |
+
|
| 924 |
+
|
| 925 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 926 |
+
- load_in_8bit: False
|
| 927 |
+
- load_in_4bit: True
|
| 928 |
+
- llm_int8_threshold: 6.0
|
| 929 |
+
- llm_int8_skip_modules: None
|
| 930 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 931 |
+
- llm_int8_has_fp16_weight: False
|
| 932 |
+
- bnb_4bit_quant_type: fp4
|
| 933 |
+
- bnb_4bit_use_double_quant: True
|
| 934 |
+
- bnb_4bit_compute_dtype: float32
|
| 935 |
+
|
| 936 |
+
### Framework versions
|
| 937 |
+
|
| 938 |
+
|
| 939 |
- 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:a20dd1da2b5cf7b8968bf8021913dce7c0e98b9e0c9029aa20725a8d34a10d57
|
| 3 |
size 21020682
|