Isabelle Cudlitz commited on
Commit ·
12a9751
1
Parent(s): 82231c5
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1404,4 +1404,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1404 |
### Framework versions
|
| 1405 |
|
| 1406 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1407 |
- PEFT 0.6.2
|
|
|
|
| 1404 |
### Framework versions
|
| 1405 |
|
| 1406 |
|
| 1407 |
+
- PEFT 0.6.2
|
| 1408 |
+
## Training procedure
|
| 1409 |
+
|
| 1410 |
+
|
| 1411 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1412 |
+
- load_in_8bit: False
|
| 1413 |
+
- load_in_4bit: True
|
| 1414 |
+
- llm_int8_threshold: 6.0
|
| 1415 |
+
- llm_int8_skip_modules: None
|
| 1416 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1417 |
+
- llm_int8_has_fp16_weight: False
|
| 1418 |
+
- bnb_4bit_quant_type: fp4
|
| 1419 |
+
- bnb_4bit_use_double_quant: True
|
| 1420 |
+
- bnb_4bit_compute_dtype: float32
|
| 1421 |
+
|
| 1422 |
+
### Framework versions
|
| 1423 |
+
|
| 1424 |
+
|
| 1425 |
- 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 sha256:12b09796460e8cc5ee8040078e56e090e5d0d353c0c76bdeea8e421b0060af9d
|
| 3 |
size 21020682
|