Isabelle Cudlitz
commited on
Commit
·
3c669b6
1
Parent(s):
ca040c8
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -540,4 +540,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 540 |
### Framework versions
|
| 541 |
|
| 542 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 543 |
- PEFT 0.6.2
|
|
|
|
| 540 |
### Framework versions
|
| 541 |
|
| 542 |
|
| 543 |
+
- PEFT 0.6.2
|
| 544 |
+
## Training procedure
|
| 545 |
+
|
| 546 |
+
|
| 547 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 548 |
+
- load_in_8bit: False
|
| 549 |
+
- load_in_4bit: True
|
| 550 |
+
- llm_int8_threshold: 6.0
|
| 551 |
+
- llm_int8_skip_modules: None
|
| 552 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 553 |
+
- llm_int8_has_fp16_weight: False
|
| 554 |
+
- bnb_4bit_quant_type: fp4
|
| 555 |
+
- bnb_4bit_use_double_quant: True
|
| 556 |
+
- bnb_4bit_compute_dtype: float32
|
| 557 |
+
|
| 558 |
+
### Framework versions
|
| 559 |
+
|
| 560 |
+
|
| 561 |
- 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 sha256:5cee070b7bd80b0cca492d184a1063cd3e88840cb746ff33fe445785111f37ce
|
| 3 |
size 21020682
|