Isabelle Cudlitz
commited on
Commit
·
8ac8a58
1
Parent(s):
5f0abd1
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1728,4 +1728,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1728 |
### Framework versions
|
| 1729 |
|
| 1730 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1731 |
- PEFT 0.6.2
|
|
|
|
| 1728 |
### Framework versions
|
| 1729 |
|
| 1730 |
|
| 1731 |
+
- PEFT 0.6.2
|
| 1732 |
+
## Training procedure
|
| 1733 |
+
|
| 1734 |
+
|
| 1735 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1736 |
+
- load_in_8bit: True
|
| 1737 |
+
- load_in_4bit: False
|
| 1738 |
+
- llm_int8_threshold: 6.0
|
| 1739 |
+
- llm_int8_skip_modules: None
|
| 1740 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1741 |
+
- llm_int8_has_fp16_weight: False
|
| 1742 |
+
- bnb_4bit_quant_type: fp4
|
| 1743 |
+
- bnb_4bit_use_double_quant: False
|
| 1744 |
+
- bnb_4bit_compute_dtype: float32
|
| 1745 |
+
|
| 1746 |
+
### Framework versions
|
| 1747 |
+
|
| 1748 |
+
|
| 1749 |
- 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 sha256:315af2fdcc8fab2f3062e6782cbbd76f824cb3608661df71fe847461b1d3fbee
|
| 3 |
size 21020682
|