Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2718,4 +2718,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2718 |
### Framework versions
|
| 2719 |
|
| 2720 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2721 |
- PEFT 0.6.2
|
|
|
|
| 2718 |
### Framework versions
|
| 2719 |
|
| 2720 |
|
| 2721 |
+
- PEFT 0.6.2
|
| 2722 |
+
## Training procedure
|
| 2723 |
+
|
| 2724 |
+
|
| 2725 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2726 |
+
- load_in_8bit: True
|
| 2727 |
+
- load_in_4bit: False
|
| 2728 |
+
- llm_int8_threshold: 6.0
|
| 2729 |
+
- llm_int8_skip_modules: None
|
| 2730 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2731 |
+
- llm_int8_has_fp16_weight: False
|
| 2732 |
+
- bnb_4bit_quant_type: fp4
|
| 2733 |
+
- bnb_4bit_use_double_quant: False
|
| 2734 |
+
- bnb_4bit_compute_dtype: float32
|
| 2735 |
+
|
| 2736 |
+
### Framework versions
|
| 2737 |
+
|
| 2738 |
+
|
| 2739 |
- 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:b8b8d477d9444fa704f6488646f389b82fa196d1619dfee27be41b4eb3f5ddb9
|
| 3 |
size 21020682
|