Isabelle Cudlitz
commited on
Commit
·
cce8b1f
1
Parent(s):
7c1b983
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -900,4 +900,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 900 |
### Framework versions
|
| 901 |
|
| 902 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 903 |
- PEFT 0.6.2
|
|
|
|
| 900 |
### Framework versions
|
| 901 |
|
| 902 |
|
| 903 |
+
- PEFT 0.6.2
|
| 904 |
+
## Training procedure
|
| 905 |
+
|
| 906 |
+
|
| 907 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 908 |
+
- load_in_8bit: False
|
| 909 |
+
- load_in_4bit: True
|
| 910 |
+
- llm_int8_threshold: 6.0
|
| 911 |
+
- llm_int8_skip_modules: None
|
| 912 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 913 |
+
- llm_int8_has_fp16_weight: False
|
| 914 |
+
- bnb_4bit_quant_type: fp4
|
| 915 |
+
- bnb_4bit_use_double_quant: True
|
| 916 |
+
- bnb_4bit_compute_dtype: float32
|
| 917 |
+
|
| 918 |
+
### Framework versions
|
| 919 |
+
|
| 920 |
+
|
| 921 |
- 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:fd7079ed2f0ea3c66dc27ec816269b066b8407b4fcd0e3da69a73e631b129525
|
| 3 |
size 21020682
|