Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1800,4 +1800,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1800 |
### Framework versions
|
| 1801 |
|
| 1802 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1803 |
- PEFT 0.6.2
|
|
|
|
| 1800 |
### Framework versions
|
| 1801 |
|
| 1802 |
|
| 1803 |
+
- PEFT 0.6.2
|
| 1804 |
+
## Training procedure
|
| 1805 |
+
|
| 1806 |
+
|
| 1807 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1808 |
+
- load_in_8bit: True
|
| 1809 |
+
- load_in_4bit: False
|
| 1810 |
+
- llm_int8_threshold: 6.0
|
| 1811 |
+
- llm_int8_skip_modules: None
|
| 1812 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1813 |
+
- llm_int8_has_fp16_weight: False
|
| 1814 |
+
- bnb_4bit_quant_type: fp4
|
| 1815 |
+
- bnb_4bit_use_double_quant: False
|
| 1816 |
+
- bnb_4bit_compute_dtype: float32
|
| 1817 |
+
|
| 1818 |
+
### Framework versions
|
| 1819 |
+
|
| 1820 |
+
|
| 1821 |
- 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:bb1ba72c05b2f15dcf27264901e543d18b12c2b1d89d0f1c03ddf23f8cdb0105
|
| 3 |
size 21020682
|