Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3816,4 +3816,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3816 |
### Framework versions
|
| 3817 |
|
| 3818 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3819 |
- PEFT 0.6.2
|
|
|
|
| 3816 |
### Framework versions
|
| 3817 |
|
| 3818 |
|
| 3819 |
+
- PEFT 0.6.2
|
| 3820 |
+
## Training procedure
|
| 3821 |
+
|
| 3822 |
+
|
| 3823 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3824 |
+
- load_in_8bit: True
|
| 3825 |
+
- load_in_4bit: False
|
| 3826 |
+
- llm_int8_threshold: 6.0
|
| 3827 |
+
- llm_int8_skip_modules: None
|
| 3828 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3829 |
+
- llm_int8_has_fp16_weight: False
|
| 3830 |
+
- bnb_4bit_quant_type: fp4
|
| 3831 |
+
- bnb_4bit_use_double_quant: False
|
| 3832 |
+
- bnb_4bit_compute_dtype: float32
|
| 3833 |
+
|
| 3834 |
+
### Framework versions
|
| 3835 |
+
|
| 3836 |
+
|
| 3837 |
- 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:f40b2d6f8616eb953803f4699a39bfa2b42af131546c760c20ee6ed7e9281e0f
|
| 3 |
size 21020682
|