Isabelle Cudlitz
commited on
Commit
·
2fab0bf
1
Parent(s):
18dd4d8
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3510,4 +3510,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3510 |
### Framework versions
|
| 3511 |
|
| 3512 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3513 |
- PEFT 0.6.2
|
|
|
|
| 3510 |
### Framework versions
|
| 3511 |
|
| 3512 |
|
| 3513 |
+
- PEFT 0.6.2
|
| 3514 |
+
## Training procedure
|
| 3515 |
+
|
| 3516 |
+
|
| 3517 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3518 |
+
- load_in_8bit: True
|
| 3519 |
+
- load_in_4bit: False
|
| 3520 |
+
- llm_int8_threshold: 6.0
|
| 3521 |
+
- llm_int8_skip_modules: None
|
| 3522 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3523 |
+
- llm_int8_has_fp16_weight: False
|
| 3524 |
+
- bnb_4bit_quant_type: fp4
|
| 3525 |
+
- bnb_4bit_use_double_quant: False
|
| 3526 |
+
- bnb_4bit_compute_dtype: float32
|
| 3527 |
+
|
| 3528 |
+
### Framework versions
|
| 3529 |
+
|
| 3530 |
+
|
| 3531 |
- 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 sha256:777eaf80dc9e6b270dd6857e1f096a322f6bbdfa766c60e885aefeba61ba29d8
|
| 3 |
size 21020682
|