Isabelle Cudlitz
commited on
Commit
·
6b47ebc
1
Parent(s):
40aba56
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1152,4 +1152,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1152 |
### Framework versions
|
| 1153 |
|
| 1154 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1155 |
- PEFT 0.6.2
|
|
|
|
| 1152 |
### Framework versions
|
| 1153 |
|
| 1154 |
|
| 1155 |
+
- PEFT 0.6.2
|
| 1156 |
+
## Training procedure
|
| 1157 |
+
|
| 1158 |
+
|
| 1159 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1160 |
+
- load_in_8bit: False
|
| 1161 |
+
- load_in_4bit: True
|
| 1162 |
+
- llm_int8_threshold: 6.0
|
| 1163 |
+
- llm_int8_skip_modules: None
|
| 1164 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1165 |
+
- llm_int8_has_fp16_weight: False
|
| 1166 |
+
- bnb_4bit_quant_type: fp4
|
| 1167 |
+
- bnb_4bit_use_double_quant: True
|
| 1168 |
+
- bnb_4bit_compute_dtype: float32
|
| 1169 |
+
|
| 1170 |
+
### Framework versions
|
| 1171 |
+
|
| 1172 |
+
|
| 1173 |
- 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 sha256:9d0668b5d1f755e61399ab2cc5d944a4f62de4f7906656447406526720ca239c
|
| 3 |
size 21020682
|