Isabelle Cudlitz
commited on
Commit
·
a3ffb12
1
Parent(s):
3c34d69
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1008,4 +1008,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1008 |
### Framework versions
|
| 1009 |
|
| 1010 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
- PEFT 0.6.2
|
|
|
|
| 1008 |
### Framework versions
|
| 1009 |
|
| 1010 |
|
| 1011 |
+
- PEFT 0.6.2
|
| 1012 |
+
## Training procedure
|
| 1013 |
+
|
| 1014 |
+
|
| 1015 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1016 |
+
- load_in_8bit: True
|
| 1017 |
+
- load_in_4bit: False
|
| 1018 |
+
- llm_int8_threshold: 6.0
|
| 1019 |
+
- llm_int8_skip_modules: None
|
| 1020 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1021 |
+
- llm_int8_has_fp16_weight: False
|
| 1022 |
+
- bnb_4bit_quant_type: fp4
|
| 1023 |
+
- bnb_4bit_use_double_quant: False
|
| 1024 |
+
- bnb_4bit_compute_dtype: float32
|
| 1025 |
+
|
| 1026 |
+
### Framework versions
|
| 1027 |
+
|
| 1028 |
+
|
| 1029 |
- 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:f5e60a9978c7349bd2b5d75678fda13d240213796110d341622120b39a1ea0b6
|
| 3 |
size 21020682
|