Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3672,4 +3672,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3672 |
### Framework versions
|
| 3673 |
|
| 3674 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3675 |
- PEFT 0.6.2
|
|
|
|
| 3672 |
### Framework versions
|
| 3673 |
|
| 3674 |
|
| 3675 |
+
- PEFT 0.6.2
|
| 3676 |
+
## Training procedure
|
| 3677 |
+
|
| 3678 |
+
|
| 3679 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3680 |
+
- load_in_8bit: True
|
| 3681 |
+
- load_in_4bit: False
|
| 3682 |
+
- llm_int8_threshold: 6.0
|
| 3683 |
+
- llm_int8_skip_modules: None
|
| 3684 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3685 |
+
- llm_int8_has_fp16_weight: False
|
| 3686 |
+
- bnb_4bit_quant_type: fp4
|
| 3687 |
+
- bnb_4bit_use_double_quant: False
|
| 3688 |
+
- bnb_4bit_compute_dtype: float32
|
| 3689 |
+
|
| 3690 |
+
### Framework versions
|
| 3691 |
+
|
| 3692 |
+
|
| 3693 |
- 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 sha256:439c94fb6862214c5b528b231acea45083debf57a8a2f90d2149e0d8ba10e72c
|
| 3 |
size 21020682
|