Isabelle Cudlitz
commited on
Commit
·
14d7547
1
Parent(s):
374a729
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3582,4 +3582,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3582 |
### Framework versions
|
| 3583 |
|
| 3584 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3585 |
- PEFT 0.6.2
|
|
|
|
| 3582 |
### Framework versions
|
| 3583 |
|
| 3584 |
|
| 3585 |
+
- PEFT 0.6.2
|
| 3586 |
+
## Training procedure
|
| 3587 |
+
|
| 3588 |
+
|
| 3589 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3590 |
+
- load_in_8bit: True
|
| 3591 |
+
- load_in_4bit: False
|
| 3592 |
+
- llm_int8_threshold: 6.0
|
| 3593 |
+
- llm_int8_skip_modules: None
|
| 3594 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3595 |
+
- llm_int8_has_fp16_weight: False
|
| 3596 |
+
- bnb_4bit_quant_type: fp4
|
| 3597 |
+
- bnb_4bit_use_double_quant: False
|
| 3598 |
+
- bnb_4bit_compute_dtype: float32
|
| 3599 |
+
|
| 3600 |
+
### Framework versions
|
| 3601 |
+
|
| 3602 |
+
|
| 3603 |
- 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 sha256:6eb5d662a84a77becc6aef02f384e87b08a2f30227ef22894e8698c0c9a25c35
|
| 3 |
size 21020682
|