Isabelle Cudlitz
commited on
Commit
·
4e79227
1
Parent(s):
21c4a6b
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3636,4 +3636,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3636 |
### Framework versions
|
| 3637 |
|
| 3638 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3639 |
- PEFT 0.6.2
|
|
|
|
| 3636 |
### Framework versions
|
| 3637 |
|
| 3638 |
|
| 3639 |
+
- PEFT 0.6.2
|
| 3640 |
+
## Training procedure
|
| 3641 |
+
|
| 3642 |
+
|
| 3643 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3644 |
+
- load_in_8bit: True
|
| 3645 |
+
- load_in_4bit: False
|
| 3646 |
+
- llm_int8_threshold: 6.0
|
| 3647 |
+
- llm_int8_skip_modules: None
|
| 3648 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3649 |
+
- llm_int8_has_fp16_weight: False
|
| 3650 |
+
- bnb_4bit_quant_type: fp4
|
| 3651 |
+
- bnb_4bit_use_double_quant: False
|
| 3652 |
+
- bnb_4bit_compute_dtype: float32
|
| 3653 |
+
|
| 3654 |
+
### Framework versions
|
| 3655 |
+
|
| 3656 |
+
|
| 3657 |
- 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 sha256:03595210cbacb25f3aa5a202843b10111f469cdb31c47c4aa51f5873a78c3e4b
|
| 3 |
size 21020682
|