Isabelle Cudlitz
commited on
Commit
·
300b23c
1
Parent(s):
99359c4
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4014,4 +4014,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4014 |
### Framework versions
|
| 4015 |
|
| 4016 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4017 |
- PEFT 0.6.2
|
|
|
|
| 4014 |
### Framework versions
|
| 4015 |
|
| 4016 |
|
| 4017 |
+
- PEFT 0.6.2
|
| 4018 |
+
## Training procedure
|
| 4019 |
+
|
| 4020 |
+
|
| 4021 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4022 |
+
- load_in_8bit: True
|
| 4023 |
+
- load_in_4bit: False
|
| 4024 |
+
- llm_int8_threshold: 6.0
|
| 4025 |
+
- llm_int8_skip_modules: None
|
| 4026 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4027 |
+
- llm_int8_has_fp16_weight: False
|
| 4028 |
+
- bnb_4bit_quant_type: fp4
|
| 4029 |
+
- bnb_4bit_use_double_quant: False
|
| 4030 |
+
- bnb_4bit_compute_dtype: float32
|
| 4031 |
+
|
| 4032 |
+
### Framework versions
|
| 4033 |
+
|
| 4034 |
+
|
| 4035 |
- 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 sha256:4e9f2b609aebe9a0f6826b7881a58c7ec161d53eb06bd0971cd547bc78cc3bae
|
| 3 |
size 21020682
|