Isabelle Cudlitz
commited on
Commit
·
ba75fc6
1
Parent(s):
8351792
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4410,4 +4410,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4410 |
### Framework versions
|
| 4411 |
|
| 4412 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4413 |
- PEFT 0.6.2
|
|
|
|
| 4410 |
### Framework versions
|
| 4411 |
|
| 4412 |
|
| 4413 |
+
- PEFT 0.6.2
|
| 4414 |
+
## Training procedure
|
| 4415 |
+
|
| 4416 |
+
|
| 4417 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4418 |
+
- load_in_8bit: True
|
| 4419 |
+
- load_in_4bit: False
|
| 4420 |
+
- llm_int8_threshold: 6.0
|
| 4421 |
+
- llm_int8_skip_modules: None
|
| 4422 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4423 |
+
- llm_int8_has_fp16_weight: False
|
| 4424 |
+
- bnb_4bit_quant_type: fp4
|
| 4425 |
+
- bnb_4bit_use_double_quant: False
|
| 4426 |
+
- bnb_4bit_compute_dtype: float32
|
| 4427 |
+
|
| 4428 |
+
### Framework versions
|
| 4429 |
+
|
| 4430 |
+
|
| 4431 |
- 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 sha256:7cac9807791af0cf166ad0071589cc7dde15b2c100c49e40207fb847d3aa8294
|
| 3 |
size 21020682
|