Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1836,4 +1836,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1836 |
### Framework versions
|
| 1837 |
|
| 1838 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1839 |
- PEFT 0.6.2
|
|
|
|
| 1836 |
### Framework versions
|
| 1837 |
|
| 1838 |
|
| 1839 |
+
- PEFT 0.6.2
|
| 1840 |
+
## Training procedure
|
| 1841 |
+
|
| 1842 |
+
|
| 1843 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1844 |
+
- load_in_8bit: True
|
| 1845 |
+
- load_in_4bit: False
|
| 1846 |
+
- llm_int8_threshold: 6.0
|
| 1847 |
+
- llm_int8_skip_modules: None
|
| 1848 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1849 |
+
- llm_int8_has_fp16_weight: False
|
| 1850 |
+
- bnb_4bit_quant_type: fp4
|
| 1851 |
+
- bnb_4bit_use_double_quant: False
|
| 1852 |
+
- bnb_4bit_compute_dtype: float32
|
| 1853 |
+
|
| 1854 |
+
### Framework versions
|
| 1855 |
+
|
| 1856 |
+
|
| 1857 |
- 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 sha256:29b810df8b1ee69aeb0ce68fe2dabac95c3925caa379fc2fcac5eecbbb9336e3
|
| 3 |
size 21020682
|