Isabelle Cudlitz
commited on
Commit
·
e3f5c56
1
Parent(s):
f12af66
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3960,4 +3960,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3960 |
### Framework versions
|
| 3961 |
|
| 3962 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3963 |
- PEFT 0.6.2
|
|
|
|
| 3960 |
### Framework versions
|
| 3961 |
|
| 3962 |
|
| 3963 |
+
- PEFT 0.6.2
|
| 3964 |
+
## Training procedure
|
| 3965 |
+
|
| 3966 |
+
|
| 3967 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3968 |
+
- load_in_8bit: True
|
| 3969 |
+
- load_in_4bit: False
|
| 3970 |
+
- llm_int8_threshold: 6.0
|
| 3971 |
+
- llm_int8_skip_modules: None
|
| 3972 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3973 |
+
- llm_int8_has_fp16_weight: False
|
| 3974 |
+
- bnb_4bit_quant_type: fp4
|
| 3975 |
+
- bnb_4bit_use_double_quant: False
|
| 3976 |
+
- bnb_4bit_compute_dtype: float32
|
| 3977 |
+
|
| 3978 |
+
### Framework versions
|
| 3979 |
+
|
| 3980 |
+
|
| 3981 |
- 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:fc7093703bb23965f1986a57c21f194b32bdba27ed9e1bee3477f50e03c4d163
|
| 3 |
size 21020682
|