Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1620,4 +1620,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1620 |
### Framework versions
|
| 1621 |
|
| 1622 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1623 |
- PEFT 0.6.2
|
|
|
|
| 1620 |
### Framework versions
|
| 1621 |
|
| 1622 |
|
| 1623 |
+
- PEFT 0.6.2
|
| 1624 |
+
## Training procedure
|
| 1625 |
+
|
| 1626 |
+
|
| 1627 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1628 |
+
- load_in_8bit: True
|
| 1629 |
+
- load_in_4bit: False
|
| 1630 |
+
- llm_int8_threshold: 6.0
|
| 1631 |
+
- llm_int8_skip_modules: None
|
| 1632 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1633 |
+
- llm_int8_has_fp16_weight: False
|
| 1634 |
+
- bnb_4bit_quant_type: fp4
|
| 1635 |
+
- bnb_4bit_use_double_quant: False
|
| 1636 |
+
- bnb_4bit_compute_dtype: float32
|
| 1637 |
+
|
| 1638 |
+
### Framework versions
|
| 1639 |
+
|
| 1640 |
+
|
| 1641 |
- 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 sha256:0dee7726442d1f7c6bb39953378c8b270233e781bb1863f07e3297380b68e501
|
| 3 |
size 21020682
|