Isabelle Cudlitz
commited on
Commit
·
98f8f2a
1
Parent(s):
45d273e
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -972,4 +972,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 972 |
### Framework versions
|
| 973 |
|
| 974 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 975 |
- PEFT 0.6.2
|
|
|
|
| 972 |
### Framework versions
|
| 973 |
|
| 974 |
|
| 975 |
+
- PEFT 0.6.2
|
| 976 |
+
## Training procedure
|
| 977 |
+
|
| 978 |
+
|
| 979 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 980 |
+
- load_in_8bit: False
|
| 981 |
+
- load_in_4bit: True
|
| 982 |
+
- llm_int8_threshold: 6.0
|
| 983 |
+
- llm_int8_skip_modules: None
|
| 984 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 985 |
+
- llm_int8_has_fp16_weight: False
|
| 986 |
+
- bnb_4bit_quant_type: fp4
|
| 987 |
+
- bnb_4bit_use_double_quant: True
|
| 988 |
+
- bnb_4bit_compute_dtype: float32
|
| 989 |
+
|
| 990 |
+
### Framework versions
|
| 991 |
+
|
| 992 |
+
|
| 993 |
- 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 sha256:13450a2fa8c1c0ca55c9971a25a9bc71fe12c4e6e4a5f817784b47ea110e29a1
|
| 3 |
size 21020682
|