Isabelle Cudlitz
commited on
Commit
·
67e405b
1
Parent(s):
e26847c
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1782,4 +1782,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1782 |
### Framework versions
|
| 1783 |
|
| 1784 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1785 |
- PEFT 0.6.2
|
|
|
|
| 1782 |
### Framework versions
|
| 1783 |
|
| 1784 |
|
| 1785 |
+
- PEFT 0.6.2
|
| 1786 |
+
## Training procedure
|
| 1787 |
+
|
| 1788 |
+
|
| 1789 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1790 |
+
- load_in_8bit: True
|
| 1791 |
+
- load_in_4bit: False
|
| 1792 |
+
- llm_int8_threshold: 6.0
|
| 1793 |
+
- llm_int8_skip_modules: None
|
| 1794 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1795 |
+
- llm_int8_has_fp16_weight: False
|
| 1796 |
+
- bnb_4bit_quant_type: fp4
|
| 1797 |
+
- bnb_4bit_use_double_quant: False
|
| 1798 |
+
- bnb_4bit_compute_dtype: float32
|
| 1799 |
+
|
| 1800 |
+
### Framework versions
|
| 1801 |
+
|
| 1802 |
+
|
| 1803 |
- 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:de5a2100f727dbdf2f01cafa3ce8eeaae6a60b865c8099889fe7173607da671a
|
| 3 |
size 21020682
|