Isabelle Cudlitz
commited on
Commit
·
179f44b
1
Parent(s):
d7e3e1e
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2988,4 +2988,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2988 |
### Framework versions
|
| 2989 |
|
| 2990 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2991 |
- PEFT 0.6.2
|
|
|
|
| 2988 |
### Framework versions
|
| 2989 |
|
| 2990 |
|
| 2991 |
+
- PEFT 0.6.2
|
| 2992 |
+
## Training procedure
|
| 2993 |
+
|
| 2994 |
+
|
| 2995 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2996 |
+
- load_in_8bit: True
|
| 2997 |
+
- load_in_4bit: False
|
| 2998 |
+
- llm_int8_threshold: 6.0
|
| 2999 |
+
- llm_int8_skip_modules: None
|
| 3000 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3001 |
+
- llm_int8_has_fp16_weight: False
|
| 3002 |
+
- bnb_4bit_quant_type: fp4
|
| 3003 |
+
- bnb_4bit_use_double_quant: False
|
| 3004 |
+
- bnb_4bit_compute_dtype: float32
|
| 3005 |
+
|
| 3006 |
+
### Framework versions
|
| 3007 |
+
|
| 3008 |
+
|
| 3009 |
- 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:d4406cfad6965821136f7d46b5bec59f63d5e9dbd5ca5696f0af745a60dda653
|
| 3 |
size 21020682
|