Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1584,4 +1584,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1584 |
### Framework versions
|
| 1585 |
|
| 1586 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1587 |
- PEFT 0.6.2
|
|
|
|
| 1584 |
### Framework versions
|
| 1585 |
|
| 1586 |
|
| 1587 |
+
- PEFT 0.6.2
|
| 1588 |
+
## Training procedure
|
| 1589 |
+
|
| 1590 |
+
|
| 1591 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1592 |
+
- load_in_8bit: True
|
| 1593 |
+
- load_in_4bit: False
|
| 1594 |
+
- llm_int8_threshold: 6.0
|
| 1595 |
+
- llm_int8_skip_modules: None
|
| 1596 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1597 |
+
- llm_int8_has_fp16_weight: False
|
| 1598 |
+
- bnb_4bit_quant_type: fp4
|
| 1599 |
+
- bnb_4bit_use_double_quant: False
|
| 1600 |
+
- bnb_4bit_compute_dtype: float32
|
| 1601 |
+
|
| 1602 |
+
### Framework versions
|
| 1603 |
+
|
| 1604 |
+
|
| 1605 |
- 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:cbbbf50ab460905cb8a9c436219986724fd1f7fb0fc69e59ea9395eb1a24c113
|
| 3 |
size 21020682
|