Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -846,4 +846,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 846 |
### Framework versions
|
| 847 |
|
| 848 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 849 |
- PEFT 0.6.2
|
|
|
|
| 846 |
### Framework versions
|
| 847 |
|
| 848 |
|
| 849 |
+
- PEFT 0.6.2
|
| 850 |
+
## Training procedure
|
| 851 |
+
|
| 852 |
+
|
| 853 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 854 |
+
- load_in_8bit: True
|
| 855 |
+
- load_in_4bit: False
|
| 856 |
+
- llm_int8_threshold: 6.0
|
| 857 |
+
- llm_int8_skip_modules: None
|
| 858 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 859 |
+
- llm_int8_has_fp16_weight: False
|
| 860 |
+
- bnb_4bit_quant_type: fp4
|
| 861 |
+
- bnb_4bit_use_double_quant: False
|
| 862 |
+
- bnb_4bit_compute_dtype: float32
|
| 863 |
+
|
| 864 |
+
### Framework versions
|
| 865 |
+
|
| 866 |
+
|
| 867 |
- 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 sha256:0d4c641bafce30ec5bfb91d65559087f119802790eea788fa225790cf189029f
|
| 3 |
size 21020682
|