Isabelle Cudlitz
commited on
Commit
·
eb9ad72
1
Parent(s):
300b23c
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4032,4 +4032,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4032 |
### Framework versions
|
| 4033 |
|
| 4034 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4035 |
- PEFT 0.6.2
|
|
|
|
| 4032 |
### Framework versions
|
| 4033 |
|
| 4034 |
|
| 4035 |
+
- PEFT 0.6.2
|
| 4036 |
+
## Training procedure
|
| 4037 |
+
|
| 4038 |
+
|
| 4039 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4040 |
+
- load_in_8bit: True
|
| 4041 |
+
- load_in_4bit: False
|
| 4042 |
+
- llm_int8_threshold: 6.0
|
| 4043 |
+
- llm_int8_skip_modules: None
|
| 4044 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4045 |
+
- llm_int8_has_fp16_weight: False
|
| 4046 |
+
- bnb_4bit_quant_type: fp4
|
| 4047 |
+
- bnb_4bit_use_double_quant: False
|
| 4048 |
+
- bnb_4bit_compute_dtype: float32
|
| 4049 |
+
|
| 4050 |
+
### Framework versions
|
| 4051 |
+
|
| 4052 |
+
|
| 4053 |
- 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 sha256:7d06d9288dbb37759836134cd6a0a70bf3a60c49227b231edf871760e1168f08
|
| 3 |
size 21020682
|