Isabelle Cudlitz commited on
Commit ·
8d10d22
1
Parent(s): 6b47ebc
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1170,4 +1170,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1170 |
### Framework versions
|
| 1171 |
|
| 1172 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1173 |
- PEFT 0.6.2
|
|
|
|
| 1170 |
### Framework versions
|
| 1171 |
|
| 1172 |
|
| 1173 |
+
- PEFT 0.6.2
|
| 1174 |
+
## Training procedure
|
| 1175 |
+
|
| 1176 |
+
|
| 1177 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1178 |
+
- load_in_8bit: False
|
| 1179 |
+
- load_in_4bit: True
|
| 1180 |
+
- llm_int8_threshold: 6.0
|
| 1181 |
+
- llm_int8_skip_modules: None
|
| 1182 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1183 |
+
- llm_int8_has_fp16_weight: False
|
| 1184 |
+
- bnb_4bit_quant_type: fp4
|
| 1185 |
+
- bnb_4bit_use_double_quant: True
|
| 1186 |
+
- bnb_4bit_compute_dtype: float32
|
| 1187 |
+
|
| 1188 |
+
### Framework versions
|
| 1189 |
+
|
| 1190 |
+
|
| 1191 |
- 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 sha256:886cba677551aa2df432d2490a2225efcd3062a383bd470f066f3f00244a479a
|
| 3 |
size 21020682
|