Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3726,4 +3726,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3726 |
### Framework versions
|
| 3727 |
|
| 3728 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3729 |
- PEFT 0.6.2
|
|
|
|
| 3726 |
### Framework versions
|
| 3727 |
|
| 3728 |
|
| 3729 |
+
- PEFT 0.6.2
|
| 3730 |
+
## Training procedure
|
| 3731 |
+
|
| 3732 |
+
|
| 3733 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3734 |
+
- load_in_8bit: True
|
| 3735 |
+
- load_in_4bit: False
|
| 3736 |
+
- llm_int8_threshold: 6.0
|
| 3737 |
+
- llm_int8_skip_modules: None
|
| 3738 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3739 |
+
- llm_int8_has_fp16_weight: False
|
| 3740 |
+
- bnb_4bit_quant_type: fp4
|
| 3741 |
+
- bnb_4bit_use_double_quant: False
|
| 3742 |
+
- bnb_4bit_compute_dtype: float32
|
| 3743 |
+
|
| 3744 |
+
### Framework versions
|
| 3745 |
+
|
| 3746 |
+
|
| 3747 |
- 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:c60ae7ce7650166836455fe605094288052abd872018acc13c37af5e5d0c954c
|
| 3 |
size 21020682
|