Isabelle Cudlitz
commited on
Commit
·
374a729
1
Parent(s):
74bcbf0
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3564,4 +3564,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3564 |
### Framework versions
|
| 3565 |
|
| 3566 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3567 |
- PEFT 0.6.2
|
|
|
|
| 3564 |
### Framework versions
|
| 3565 |
|
| 3566 |
|
| 3567 |
+
- PEFT 0.6.2
|
| 3568 |
+
## Training procedure
|
| 3569 |
+
|
| 3570 |
+
|
| 3571 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3572 |
+
- load_in_8bit: True
|
| 3573 |
+
- load_in_4bit: False
|
| 3574 |
+
- llm_int8_threshold: 6.0
|
| 3575 |
+
- llm_int8_skip_modules: None
|
| 3576 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3577 |
+
- llm_int8_has_fp16_weight: False
|
| 3578 |
+
- bnb_4bit_quant_type: fp4
|
| 3579 |
+
- bnb_4bit_use_double_quant: False
|
| 3580 |
+
- bnb_4bit_compute_dtype: float32
|
| 3581 |
+
|
| 3582 |
+
### Framework versions
|
| 3583 |
+
|
| 3584 |
+
|
| 3585 |
- 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:c653004c0ee9e0758743eb399005aef56495029fb897ca0f9216534f6124bd7c
|
| 3 |
size 21020682
|