Isabelle Cudlitz
commited on
Commit
·
e7da36c
1
Parent(s):
4301b18
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1980,4 +1980,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1980 |
### Framework versions
|
| 1981 |
|
| 1982 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1983 |
- PEFT 0.6.2
|
|
|
|
| 1980 |
### Framework versions
|
| 1981 |
|
| 1982 |
|
| 1983 |
+
- PEFT 0.6.2
|
| 1984 |
+
## Training procedure
|
| 1985 |
+
|
| 1986 |
+
|
| 1987 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1988 |
+
- load_in_8bit: True
|
| 1989 |
+
- load_in_4bit: False
|
| 1990 |
+
- llm_int8_threshold: 6.0
|
| 1991 |
+
- llm_int8_skip_modules: None
|
| 1992 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1993 |
+
- llm_int8_has_fp16_weight: False
|
| 1994 |
+
- bnb_4bit_quant_type: fp4
|
| 1995 |
+
- bnb_4bit_use_double_quant: False
|
| 1996 |
+
- bnb_4bit_compute_dtype: float32
|
| 1997 |
+
|
| 1998 |
+
### Framework versions
|
| 1999 |
+
|
| 2000 |
+
|
| 2001 |
- 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 sha256:40a05b78bff74dbeef378b7551085a4e9ec50c379dd2076c03a9a41ad513a408
|
| 3 |
size 21020682
|