Isabelle Cudlitz
commited on
Commit
·
5b005fa
1
Parent(s):
fab3c3f
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -450,4 +450,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 450 |
### Framework versions
|
| 451 |
|
| 452 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 453 |
- PEFT 0.6.2
|
|
|
|
| 450 |
### Framework versions
|
| 451 |
|
| 452 |
|
| 453 |
+
- PEFT 0.6.2
|
| 454 |
+
## Training procedure
|
| 455 |
+
|
| 456 |
+
|
| 457 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 458 |
+
- load_in_8bit: False
|
| 459 |
+
- load_in_4bit: True
|
| 460 |
+
- llm_int8_threshold: 6.0
|
| 461 |
+
- llm_int8_skip_modules: None
|
| 462 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 463 |
+
- llm_int8_has_fp16_weight: False
|
| 464 |
+
- bnb_4bit_quant_type: fp4
|
| 465 |
+
- bnb_4bit_use_double_quant: True
|
| 466 |
+
- bnb_4bit_compute_dtype: float32
|
| 467 |
+
|
| 468 |
+
### Framework versions
|
| 469 |
+
|
| 470 |
+
|
| 471 |
- 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:afba351f75274ee3b702505062c6d6a89f45e72f6ce765cc803dea02ed5eee66
|
| 3 |
size 21020682
|