Isabelle Cudlitz
commited on
Commit
·
d61c783
1
Parent(s):
12a9751
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1422,4 +1422,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1422 |
### Framework versions
|
| 1423 |
|
| 1424 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1425 |
- PEFT 0.6.2
|
|
|
|
| 1422 |
### Framework versions
|
| 1423 |
|
| 1424 |
|
| 1425 |
+
- PEFT 0.6.2
|
| 1426 |
+
## Training procedure
|
| 1427 |
+
|
| 1428 |
+
|
| 1429 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1430 |
+
- load_in_8bit: False
|
| 1431 |
+
- load_in_4bit: True
|
| 1432 |
+
- llm_int8_threshold: 6.0
|
| 1433 |
+
- llm_int8_skip_modules: None
|
| 1434 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1435 |
+
- llm_int8_has_fp16_weight: False
|
| 1436 |
+
- bnb_4bit_quant_type: fp4
|
| 1437 |
+
- bnb_4bit_use_double_quant: True
|
| 1438 |
+
- bnb_4bit_compute_dtype: float32
|
| 1439 |
+
|
| 1440 |
+
### Framework versions
|
| 1441 |
+
|
| 1442 |
+
|
| 1443 |
- 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 sha256:9e198d77639a9e2eda083001650f4592eaa944db1bfe32384e9a2cfb01eb8c64
|
| 3 |
size 21020682
|