Isabelle Cudlitz
commited on
Commit
·
5f0abd1
1
Parent(s):
c5ccdae
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1710,4 +1710,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1710 |
### Framework versions
|
| 1711 |
|
| 1712 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1713 |
- PEFT 0.6.2
|
|
|
|
| 1710 |
### Framework versions
|
| 1711 |
|
| 1712 |
|
| 1713 |
+
- PEFT 0.6.2
|
| 1714 |
+
## Training procedure
|
| 1715 |
+
|
| 1716 |
+
|
| 1717 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1718 |
+
- load_in_8bit: True
|
| 1719 |
+
- load_in_4bit: False
|
| 1720 |
+
- llm_int8_threshold: 6.0
|
| 1721 |
+
- llm_int8_skip_modules: None
|
| 1722 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1723 |
+
- llm_int8_has_fp16_weight: False
|
| 1724 |
+
- bnb_4bit_quant_type: fp4
|
| 1725 |
+
- bnb_4bit_use_double_quant: False
|
| 1726 |
+
- bnb_4bit_compute_dtype: float32
|
| 1727 |
+
|
| 1728 |
+
### Framework versions
|
| 1729 |
+
|
| 1730 |
+
|
| 1731 |
- 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:ee1d210b5ed3823bba347d6675c9a70ac4be3137d861b15bbe9ddda5ce470373
|
| 3 |
size 21020682
|