Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2646,4 +2646,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2646 |
### Framework versions
|
| 2647 |
|
| 2648 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2649 |
- PEFT 0.6.2
|
|
|
|
| 2646 |
### Framework versions
|
| 2647 |
|
| 2648 |
|
| 2649 |
+
- PEFT 0.6.2
|
| 2650 |
+
## Training procedure
|
| 2651 |
+
|
| 2652 |
+
|
| 2653 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2654 |
+
- load_in_8bit: True
|
| 2655 |
+
- load_in_4bit: False
|
| 2656 |
+
- llm_int8_threshold: 6.0
|
| 2657 |
+
- llm_int8_skip_modules: None
|
| 2658 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2659 |
+
- llm_int8_has_fp16_weight: False
|
| 2660 |
+
- bnb_4bit_quant_type: fp4
|
| 2661 |
+
- bnb_4bit_use_double_quant: False
|
| 2662 |
+
- bnb_4bit_compute_dtype: float32
|
| 2663 |
+
|
| 2664 |
+
### Framework versions
|
| 2665 |
+
|
| 2666 |
+
|
| 2667 |
- 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 sha256:9832d2fbac20b235f35b21dc51e03bab670163f292b4ad1e5b8f6a758a9d857f
|
| 3 |
size 21020682
|