Isabelle Cudlitz
commited on
Commit
·
94467ee
1
Parent(s):
e42bdd6
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2682,4 +2682,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2682 |
### Framework versions
|
| 2683 |
|
| 2684 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2685 |
- PEFT 0.6.2
|
|
|
|
| 2682 |
### Framework versions
|
| 2683 |
|
| 2684 |
|
| 2685 |
+
- PEFT 0.6.2
|
| 2686 |
+
## Training procedure
|
| 2687 |
+
|
| 2688 |
+
|
| 2689 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2690 |
+
- load_in_8bit: True
|
| 2691 |
+
- load_in_4bit: False
|
| 2692 |
+
- llm_int8_threshold: 6.0
|
| 2693 |
+
- llm_int8_skip_modules: None
|
| 2694 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2695 |
+
- llm_int8_has_fp16_weight: False
|
| 2696 |
+
- bnb_4bit_quant_type: fp4
|
| 2697 |
+
- bnb_4bit_use_double_quant: False
|
| 2698 |
+
- bnb_4bit_compute_dtype: float32
|
| 2699 |
+
|
| 2700 |
+
### Framework versions
|
| 2701 |
+
|
| 2702 |
+
|
| 2703 |
- 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:e21cf9ba879c8ea46ea2c53a1d0e84231cf623f8bb685098633080c7f90974d1
|
| 3 |
size 21020682
|