Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3762,4 +3762,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3762 |
### Framework versions
|
| 3763 |
|
| 3764 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3765 |
- PEFT 0.6.2
|
|
|
|
| 3762 |
### Framework versions
|
| 3763 |
|
| 3764 |
|
| 3765 |
+
- PEFT 0.6.2
|
| 3766 |
+
## Training procedure
|
| 3767 |
+
|
| 3768 |
+
|
| 3769 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3770 |
+
- load_in_8bit: True
|
| 3771 |
+
- load_in_4bit: False
|
| 3772 |
+
- llm_int8_threshold: 6.0
|
| 3773 |
+
- llm_int8_skip_modules: None
|
| 3774 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3775 |
+
- llm_int8_has_fp16_weight: False
|
| 3776 |
+
- bnb_4bit_quant_type: fp4
|
| 3777 |
+
- bnb_4bit_use_double_quant: False
|
| 3778 |
+
- bnb_4bit_compute_dtype: float32
|
| 3779 |
+
|
| 3780 |
+
### Framework versions
|
| 3781 |
+
|
| 3782 |
+
|
| 3783 |
- 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:b6e2229acc51877c0f7f332bf267bd381bf7fabf46e9d69e6b89e5706d15dcc5
|
| 3 |
size 21020682
|