Isabelle Cudlitz
commited on
Commit
·
95ebc74
1
Parent(s):
5e19a57
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2628,4 +2628,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2628 |
### Framework versions
|
| 2629 |
|
| 2630 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2631 |
- PEFT 0.6.2
|
|
|
|
| 2628 |
### Framework versions
|
| 2629 |
|
| 2630 |
|
| 2631 |
+
- PEFT 0.6.2
|
| 2632 |
+
## Training procedure
|
| 2633 |
+
|
| 2634 |
+
|
| 2635 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2636 |
+
- load_in_8bit: True
|
| 2637 |
+
- load_in_4bit: False
|
| 2638 |
+
- llm_int8_threshold: 6.0
|
| 2639 |
+
- llm_int8_skip_modules: None
|
| 2640 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2641 |
+
- llm_int8_has_fp16_weight: False
|
| 2642 |
+
- bnb_4bit_quant_type: fp4
|
| 2643 |
+
- bnb_4bit_use_double_quant: False
|
| 2644 |
+
- bnb_4bit_compute_dtype: float32
|
| 2645 |
+
|
| 2646 |
+
### Framework versions
|
| 2647 |
+
|
| 2648 |
+
|
| 2649 |
- 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 sha256:5aaccff8cc38456806a024a0648c454c2d616d0d67663b891b5ac8f2bfd89117
|
| 3 |
size 21020682
|