Isabelle Cudlitz
commited on
Commit
·
c1c249c
1
Parent(s):
8ac8a58
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1746,4 +1746,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1746 |
### Framework versions
|
| 1747 |
|
| 1748 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1749 |
- PEFT 0.6.2
|
|
|
|
| 1746 |
### Framework versions
|
| 1747 |
|
| 1748 |
|
| 1749 |
+
- PEFT 0.6.2
|
| 1750 |
+
## Training procedure
|
| 1751 |
+
|
| 1752 |
+
|
| 1753 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1754 |
+
- load_in_8bit: True
|
| 1755 |
+
- load_in_4bit: False
|
| 1756 |
+
- llm_int8_threshold: 6.0
|
| 1757 |
+
- llm_int8_skip_modules: None
|
| 1758 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1759 |
+
- llm_int8_has_fp16_weight: False
|
| 1760 |
+
- bnb_4bit_quant_type: fp4
|
| 1761 |
+
- bnb_4bit_use_double_quant: False
|
| 1762 |
+
- bnb_4bit_compute_dtype: float32
|
| 1763 |
+
|
| 1764 |
+
### Framework versions
|
| 1765 |
+
|
| 1766 |
+
|
| 1767 |
- 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 sha256:5d06c4f95d400e7aa427c837e9a6fe7ad11263520de9dd9d7c71726e59e60279
|
| 3 |
size 21020682
|