Isabelle Cudlitz
commited on
Commit
·
4779511
1
Parent(s):
4a7ba66
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1638,4 +1638,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1638 |
### Framework versions
|
| 1639 |
|
| 1640 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1641 |
- PEFT 0.6.2
|
|
|
|
| 1638 |
### Framework versions
|
| 1639 |
|
| 1640 |
|
| 1641 |
+
- PEFT 0.6.2
|
| 1642 |
+
## Training procedure
|
| 1643 |
+
|
| 1644 |
+
|
| 1645 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1646 |
+
- load_in_8bit: True
|
| 1647 |
+
- load_in_4bit: False
|
| 1648 |
+
- llm_int8_threshold: 6.0
|
| 1649 |
+
- llm_int8_skip_modules: None
|
| 1650 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1651 |
+
- llm_int8_has_fp16_weight: False
|
| 1652 |
+
- bnb_4bit_quant_type: fp4
|
| 1653 |
+
- bnb_4bit_use_double_quant: False
|
| 1654 |
+
- bnb_4bit_compute_dtype: float32
|
| 1655 |
+
|
| 1656 |
+
### Framework versions
|
| 1657 |
+
|
| 1658 |
+
|
| 1659 |
- 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 sha256:25874398fe022878b809fe21d89ccb68c44e655aa968ee0843e9c69215f51f7c
|
| 3 |
size 21020682
|