Isabelle Cudlitz
commited on
Commit
·
84304e9
1
Parent(s):
25a578a
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1026,4 +1026,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1026 |
### Framework versions
|
| 1027 |
|
| 1028 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1029 |
- PEFT 0.6.2
|
|
|
|
| 1026 |
### Framework versions
|
| 1027 |
|
| 1028 |
|
| 1029 |
+
- PEFT 0.6.2
|
| 1030 |
+
## Training procedure
|
| 1031 |
+
|
| 1032 |
+
|
| 1033 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1034 |
+
- load_in_8bit: False
|
| 1035 |
+
- load_in_4bit: True
|
| 1036 |
+
- llm_int8_threshold: 6.0
|
| 1037 |
+
- llm_int8_skip_modules: None
|
| 1038 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1039 |
+
- llm_int8_has_fp16_weight: False
|
| 1040 |
+
- bnb_4bit_quant_type: fp4
|
| 1041 |
+
- bnb_4bit_use_double_quant: True
|
| 1042 |
+
- bnb_4bit_compute_dtype: float32
|
| 1043 |
+
|
| 1044 |
+
### Framework versions
|
| 1045 |
+
|
| 1046 |
+
|
| 1047 |
- 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 sha256:6a29d69f7d2b198bb818f56eb060166425141629eef8cee472d8d509c575bf88
|
| 3 |
size 21020682
|