Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1854,4 +1854,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1854 |
### Framework versions
|
| 1855 |
|
| 1856 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1857 |
- PEFT 0.6.2
|
|
|
|
| 1854 |
### Framework versions
|
| 1855 |
|
| 1856 |
|
| 1857 |
+
- PEFT 0.6.2
|
| 1858 |
+
## Training procedure
|
| 1859 |
+
|
| 1860 |
+
|
| 1861 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1862 |
+
- load_in_8bit: True
|
| 1863 |
+
- load_in_4bit: False
|
| 1864 |
+
- llm_int8_threshold: 6.0
|
| 1865 |
+
- llm_int8_skip_modules: None
|
| 1866 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1867 |
+
- llm_int8_has_fp16_weight: False
|
| 1868 |
+
- bnb_4bit_quant_type: fp4
|
| 1869 |
+
- bnb_4bit_use_double_quant: False
|
| 1870 |
+
- bnb_4bit_compute_dtype: float32
|
| 1871 |
+
|
| 1872 |
+
### Framework versions
|
| 1873 |
+
|
| 1874 |
+
|
| 1875 |
- 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 sha256:392ba190fa5262b695e7e37c47a7ba57f8abacdde0cfe77ed2dd6a08516fe16e
|
| 3 |
size 21020682
|