Isabelle Cudlitz
commited on
Commit
·
d113f7c
1
Parent(s):
8d10d22
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1188,4 +1188,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1188 |
### Framework versions
|
| 1189 |
|
| 1190 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1191 |
- PEFT 0.6.2
|
|
|
|
| 1188 |
### Framework versions
|
| 1189 |
|
| 1190 |
|
| 1191 |
+
- PEFT 0.6.2
|
| 1192 |
+
## Training procedure
|
| 1193 |
+
|
| 1194 |
+
|
| 1195 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1196 |
+
- load_in_8bit: False
|
| 1197 |
+
- load_in_4bit: True
|
| 1198 |
+
- llm_int8_threshold: 6.0
|
| 1199 |
+
- llm_int8_skip_modules: None
|
| 1200 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1201 |
+
- llm_int8_has_fp16_weight: False
|
| 1202 |
+
- bnb_4bit_quant_type: fp4
|
| 1203 |
+
- bnb_4bit_use_double_quant: True
|
| 1204 |
+
- bnb_4bit_compute_dtype: float32
|
| 1205 |
+
|
| 1206 |
+
### Framework versions
|
| 1207 |
+
|
| 1208 |
+
|
| 1209 |
- 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 sha256:1b1473083e36ddbffb41911cd53a7b70d99be03e31d517abd0a3b3c245460c4f
|
| 3 |
size 21020682
|