Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3798,4 +3798,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3798 |
### Framework versions
|
| 3799 |
|
| 3800 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3801 |
- PEFT 0.6.2
|
|
|
|
| 3798 |
### Framework versions
|
| 3799 |
|
| 3800 |
|
| 3801 |
+
- PEFT 0.6.2
|
| 3802 |
+
## Training procedure
|
| 3803 |
+
|
| 3804 |
+
|
| 3805 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3806 |
+
- load_in_8bit: True
|
| 3807 |
+
- load_in_4bit: False
|
| 3808 |
+
- llm_int8_threshold: 6.0
|
| 3809 |
+
- llm_int8_skip_modules: None
|
| 3810 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3811 |
+
- llm_int8_has_fp16_weight: False
|
| 3812 |
+
- bnb_4bit_quant_type: fp4
|
| 3813 |
+
- bnb_4bit_use_double_quant: False
|
| 3814 |
+
- bnb_4bit_compute_dtype: float32
|
| 3815 |
+
|
| 3816 |
+
### Framework versions
|
| 3817 |
+
|
| 3818 |
+
|
| 3819 |
- 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:d8e33f50bd1127be2a3eed70c57ed1d1a4f06812f1a50bb4e72ac2826bf43a4e
|
| 3 |
size 21020682
|