Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3888,4 +3888,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3888 |
### Framework versions
|
| 3889 |
|
| 3890 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3891 |
- PEFT 0.6.2
|
|
|
|
| 3888 |
### Framework versions
|
| 3889 |
|
| 3890 |
|
| 3891 |
+
- PEFT 0.6.2
|
| 3892 |
+
## Training procedure
|
| 3893 |
+
|
| 3894 |
+
|
| 3895 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3896 |
+
- load_in_8bit: True
|
| 3897 |
+
- load_in_4bit: False
|
| 3898 |
+
- llm_int8_threshold: 6.0
|
| 3899 |
+
- llm_int8_skip_modules: None
|
| 3900 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3901 |
+
- llm_int8_has_fp16_weight: False
|
| 3902 |
+
- bnb_4bit_quant_type: fp4
|
| 3903 |
+
- bnb_4bit_use_double_quant: False
|
| 3904 |
+
- bnb_4bit_compute_dtype: float32
|
| 3905 |
+
|
| 3906 |
+
### Framework versions
|
| 3907 |
+
|
| 3908 |
+
|
| 3909 |
- 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:e9c6c5b65adefbd8d92a4ee32089537507a984131c3c849e8a50469508954feb
|
| 3 |
size 21020682
|