Isabelle Cudlitz
commited on
Commit
·
7a92f8d
1
Parent(s):
a36d935
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3366,4 +3366,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3366 |
### Framework versions
|
| 3367 |
|
| 3368 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3369 |
- PEFT 0.6.2
|
|
|
|
| 3366 |
### Framework versions
|
| 3367 |
|
| 3368 |
|
| 3369 |
+
- PEFT 0.6.2
|
| 3370 |
+
## Training procedure
|
| 3371 |
+
|
| 3372 |
+
|
| 3373 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3374 |
+
- load_in_8bit: True
|
| 3375 |
+
- load_in_4bit: False
|
| 3376 |
+
- llm_int8_threshold: 6.0
|
| 3377 |
+
- llm_int8_skip_modules: None
|
| 3378 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3379 |
+
- llm_int8_has_fp16_weight: False
|
| 3380 |
+
- bnb_4bit_quant_type: fp4
|
| 3381 |
+
- bnb_4bit_use_double_quant: False
|
| 3382 |
+
- bnb_4bit_compute_dtype: float32
|
| 3383 |
+
|
| 3384 |
+
### Framework versions
|
| 3385 |
+
|
| 3386 |
+
|
| 3387 |
- 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 sha256:5617ecc7f996fea45b3337247bbe2cb6bd9ce4b82704714b55f31311d73626be
|
| 3 |
size 21020682
|