Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1656,4 +1656,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1656 |
### Framework versions
|
| 1657 |
|
| 1658 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1659 |
- PEFT 0.6.2
|
|
|
|
| 1656 |
### Framework versions
|
| 1657 |
|
| 1658 |
|
| 1659 |
+
- PEFT 0.6.2
|
| 1660 |
+
## Training procedure
|
| 1661 |
+
|
| 1662 |
+
|
| 1663 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1664 |
+
- load_in_8bit: True
|
| 1665 |
+
- load_in_4bit: False
|
| 1666 |
+
- llm_int8_threshold: 6.0
|
| 1667 |
+
- llm_int8_skip_modules: None
|
| 1668 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1669 |
+
- llm_int8_has_fp16_weight: False
|
| 1670 |
+
- bnb_4bit_quant_type: fp4
|
| 1671 |
+
- bnb_4bit_use_double_quant: False
|
| 1672 |
+
- bnb_4bit_compute_dtype: float32
|
| 1673 |
+
|
| 1674 |
+
### Framework versions
|
| 1675 |
+
|
| 1676 |
+
|
| 1677 |
- 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:efaf950ba8d7edee65acc0524110a12371a6250523317626dffc3d63b140f23f
|
| 3 |
size 21020682
|