Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -648,4 +648,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 648 |
### Framework versions
|
| 649 |
|
| 650 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 651 |
- PEFT 0.6.2
|
|
|
|
| 648 |
### Framework versions
|
| 649 |
|
| 650 |
|
| 651 |
+
- PEFT 0.6.2
|
| 652 |
+
## Training procedure
|
| 653 |
+
|
| 654 |
+
|
| 655 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 656 |
+
- load_in_8bit: True
|
| 657 |
+
- load_in_4bit: False
|
| 658 |
+
- llm_int8_threshold: 6.0
|
| 659 |
+
- llm_int8_skip_modules: None
|
| 660 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 661 |
+
- llm_int8_has_fp16_weight: False
|
| 662 |
+
- bnb_4bit_quant_type: fp4
|
| 663 |
+
- bnb_4bit_use_double_quant: False
|
| 664 |
+
- bnb_4bit_compute_dtype: float32
|
| 665 |
+
|
| 666 |
+
### Framework versions
|
| 667 |
+
|
| 668 |
+
|
| 669 |
- 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:e6f08bbd2e92851b76b750b184445ef6c245f29b65d3b28670479f34df26410c
|
| 3 |
size 21020682
|