Isabelle Cudlitz
commited on
Commit
·
e42bdd6
1
Parent(s):
c72dff7
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2664,4 +2664,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2664 |
### Framework versions
|
| 2665 |
|
| 2666 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2667 |
- PEFT 0.6.2
|
|
|
|
| 2664 |
### Framework versions
|
| 2665 |
|
| 2666 |
|
| 2667 |
+
- PEFT 0.6.2
|
| 2668 |
+
## Training procedure
|
| 2669 |
+
|
| 2670 |
+
|
| 2671 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2672 |
+
- load_in_8bit: True
|
| 2673 |
+
- load_in_4bit: False
|
| 2674 |
+
- llm_int8_threshold: 6.0
|
| 2675 |
+
- llm_int8_skip_modules: None
|
| 2676 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2677 |
+
- llm_int8_has_fp16_weight: False
|
| 2678 |
+
- bnb_4bit_quant_type: fp4
|
| 2679 |
+
- bnb_4bit_use_double_quant: False
|
| 2680 |
+
- bnb_4bit_compute_dtype: float32
|
| 2681 |
+
|
| 2682 |
+
### Framework versions
|
| 2683 |
+
|
| 2684 |
+
|
| 2685 |
- 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 sha256:93dad1e1aee048e6cd9e0aa2f8510cadbb0aaba1b1b72bef31fd3240c2642bb9
|
| 3 |
size 21020682
|