Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1674,4 +1674,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1674 |
### Framework versions
|
| 1675 |
|
| 1676 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1677 |
- PEFT 0.6.2
|
|
|
|
| 1674 |
### Framework versions
|
| 1675 |
|
| 1676 |
|
| 1677 |
+
- PEFT 0.6.2
|
| 1678 |
+
## Training procedure
|
| 1679 |
+
|
| 1680 |
+
|
| 1681 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1682 |
+
- load_in_8bit: True
|
| 1683 |
+
- load_in_4bit: False
|
| 1684 |
+
- llm_int8_threshold: 6.0
|
| 1685 |
+
- llm_int8_skip_modules: None
|
| 1686 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1687 |
+
- llm_int8_has_fp16_weight: False
|
| 1688 |
+
- bnb_4bit_quant_type: fp4
|
| 1689 |
+
- bnb_4bit_use_double_quant: False
|
| 1690 |
+
- bnb_4bit_compute_dtype: float32
|
| 1691 |
+
|
| 1692 |
+
### Framework versions
|
| 1693 |
+
|
| 1694 |
+
|
| 1695 |
- 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 sha256:0bee9f62627153b83226775f07b13435f7c77d060f96cb2898fb4e07eeba640f
|
| 3 |
size 21020682
|