Isabelle Cudlitz
commited on
Commit
·
c1b8c5c
1
Parent(s):
af45acf
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1818,4 +1818,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1818 |
### Framework versions
|
| 1819 |
|
| 1820 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1821 |
- PEFT 0.6.2
|
|
|
|
| 1818 |
### Framework versions
|
| 1819 |
|
| 1820 |
|
| 1821 |
+
- PEFT 0.6.2
|
| 1822 |
+
## Training procedure
|
| 1823 |
+
|
| 1824 |
+
|
| 1825 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1826 |
+
- load_in_8bit: True
|
| 1827 |
+
- load_in_4bit: False
|
| 1828 |
+
- llm_int8_threshold: 6.0
|
| 1829 |
+
- llm_int8_skip_modules: None
|
| 1830 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1831 |
+
- llm_int8_has_fp16_weight: False
|
| 1832 |
+
- bnb_4bit_quant_type: fp4
|
| 1833 |
+
- bnb_4bit_use_double_quant: False
|
| 1834 |
+
- bnb_4bit_compute_dtype: float32
|
| 1835 |
+
|
| 1836 |
+
### Framework versions
|
| 1837 |
+
|
| 1838 |
+
|
| 1839 |
- 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 sha256:6536d822389e8af994602992015730eb735c4fbbf80187f802e2baa4a2b6a6f0
|
| 3 |
size 21020682
|