Isabelle Cudlitz
commited on
Commit
·
21c7982
1
Parent(s):
3ce9463
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1314,4 +1314,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1314 |
### Framework versions
|
| 1315 |
|
| 1316 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1317 |
- PEFT 0.6.2
|
|
|
|
| 1314 |
### Framework versions
|
| 1315 |
|
| 1316 |
|
| 1317 |
+
- PEFT 0.6.2
|
| 1318 |
+
## Training procedure
|
| 1319 |
+
|
| 1320 |
+
|
| 1321 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1322 |
+
- load_in_8bit: True
|
| 1323 |
+
- load_in_4bit: False
|
| 1324 |
+
- llm_int8_threshold: 6.0
|
| 1325 |
+
- llm_int8_skip_modules: None
|
| 1326 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1327 |
+
- llm_int8_has_fp16_weight: False
|
| 1328 |
+
- bnb_4bit_quant_type: fp4
|
| 1329 |
+
- bnb_4bit_use_double_quant: False
|
| 1330 |
+
- bnb_4bit_compute_dtype: float32
|
| 1331 |
+
|
| 1332 |
+
### Framework versions
|
| 1333 |
+
|
| 1334 |
+
|
| 1335 |
- 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 sha256:68004ca2eeb5715b0390d0362700a688a4c00597b77f91c1ea742cc117840fb6
|
| 3 |
size 21020682
|