Isabelle Cudlitz
commited on
Commit
·
6060174
1
Parent(s):
854a2ef
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2592,4 +2592,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2592 |
### Framework versions
|
| 2593 |
|
| 2594 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2595 |
- PEFT 0.6.2
|
|
|
|
| 2592 |
### Framework versions
|
| 2593 |
|
| 2594 |
|
| 2595 |
+
- PEFT 0.6.2
|
| 2596 |
+
## Training procedure
|
| 2597 |
+
|
| 2598 |
+
|
| 2599 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2600 |
+
- load_in_8bit: True
|
| 2601 |
+
- load_in_4bit: False
|
| 2602 |
+
- llm_int8_threshold: 6.0
|
| 2603 |
+
- llm_int8_skip_modules: None
|
| 2604 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2605 |
+
- llm_int8_has_fp16_weight: False
|
| 2606 |
+
- bnb_4bit_quant_type: fp4
|
| 2607 |
+
- bnb_4bit_use_double_quant: False
|
| 2608 |
+
- bnb_4bit_compute_dtype: float32
|
| 2609 |
+
|
| 2610 |
+
### Framework versions
|
| 2611 |
+
|
| 2612 |
+
|
| 2613 |
- 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 sha256:3db78219ae6bf58fcf08b75998ce88565a9c402d19923200798008946ea71438
|
| 3 |
size 21020682
|