Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2862,4 +2862,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2862 |
### Framework versions
|
| 2863 |
|
| 2864 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2865 |
- PEFT 0.6.2
|
|
|
|
| 2862 |
### Framework versions
|
| 2863 |
|
| 2864 |
|
| 2865 |
+
- PEFT 0.6.2
|
| 2866 |
+
## Training procedure
|
| 2867 |
+
|
| 2868 |
+
|
| 2869 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2870 |
+
- load_in_8bit: True
|
| 2871 |
+
- load_in_4bit: False
|
| 2872 |
+
- llm_int8_threshold: 6.0
|
| 2873 |
+
- llm_int8_skip_modules: None
|
| 2874 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2875 |
+
- llm_int8_has_fp16_weight: False
|
| 2876 |
+
- bnb_4bit_quant_type: fp4
|
| 2877 |
+
- bnb_4bit_use_double_quant: False
|
| 2878 |
+
- bnb_4bit_compute_dtype: float32
|
| 2879 |
+
|
| 2880 |
+
### Framework versions
|
| 2881 |
+
|
| 2882 |
+
|
| 2883 |
- 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:bfa3083b31dc58b55e2571318effe06aa42bbdeafc8da2afbab0fe96d2df2d57
|
| 3 |
size 21020682
|