Isabelle Cudlitz commited on
Commit ·
3630625
1
Parent(s): 09d33e0
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -810,4 +810,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 810 |
### Framework versions
|
| 811 |
|
| 812 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 813 |
- PEFT 0.6.2
|
|
|
|
| 810 |
### Framework versions
|
| 811 |
|
| 812 |
|
| 813 |
+
- PEFT 0.6.2
|
| 814 |
+
## Training procedure
|
| 815 |
+
|
| 816 |
+
|
| 817 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 818 |
+
- load_in_8bit: False
|
| 819 |
+
- load_in_4bit: True
|
| 820 |
+
- llm_int8_threshold: 6.0
|
| 821 |
+
- llm_int8_skip_modules: None
|
| 822 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 823 |
+
- llm_int8_has_fp16_weight: False
|
| 824 |
+
- bnb_4bit_quant_type: fp4
|
| 825 |
+
- bnb_4bit_use_double_quant: True
|
| 826 |
+
- bnb_4bit_compute_dtype: float32
|
| 827 |
+
|
| 828 |
+
### Framework versions
|
| 829 |
+
|
| 830 |
+
|
| 831 |
- 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 sha256:98d17348da763dd5da01c34149a0cbfdc7467b14c9d240b23dffa00a5c3ad38d
|
| 3 |
size 21020682
|