Isabelle Cudlitz
commited on
Commit
·
b8d88f9
1
Parent(s):
4db125b
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2826,4 +2826,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2826 |
### Framework versions
|
| 2827 |
|
| 2828 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2829 |
- PEFT 0.6.2
|
|
|
|
| 2826 |
### Framework versions
|
| 2827 |
|
| 2828 |
|
| 2829 |
+
- PEFT 0.6.2
|
| 2830 |
+
## Training procedure
|
| 2831 |
+
|
| 2832 |
+
|
| 2833 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2834 |
+
- load_in_8bit: True
|
| 2835 |
+
- load_in_4bit: False
|
| 2836 |
+
- llm_int8_threshold: 6.0
|
| 2837 |
+
- llm_int8_skip_modules: None
|
| 2838 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2839 |
+
- llm_int8_has_fp16_weight: False
|
| 2840 |
+
- bnb_4bit_quant_type: fp4
|
| 2841 |
+
- bnb_4bit_use_double_quant: False
|
| 2842 |
+
- bnb_4bit_compute_dtype: float32
|
| 2843 |
+
|
| 2844 |
+
### Framework versions
|
| 2845 |
+
|
| 2846 |
+
|
| 2847 |
- 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 sha256:37ed8098a776a369dabedc666cae8a19f4d9dc7bdd3f9f73b977fbdbf4f5a0a7
|
| 3 |
size 21020682
|