Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3546,4 +3546,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3546 |
### Framework versions
|
| 3547 |
|
| 3548 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3549 |
- PEFT 0.6.2
|
|
|
|
| 3546 |
### Framework versions
|
| 3547 |
|
| 3548 |
|
| 3549 |
+
- PEFT 0.6.2
|
| 3550 |
+
## Training procedure
|
| 3551 |
+
|
| 3552 |
+
|
| 3553 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3554 |
+
- load_in_8bit: True
|
| 3555 |
+
- load_in_4bit: False
|
| 3556 |
+
- llm_int8_threshold: 6.0
|
| 3557 |
+
- llm_int8_skip_modules: None
|
| 3558 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3559 |
+
- llm_int8_has_fp16_weight: False
|
| 3560 |
+
- bnb_4bit_quant_type: fp4
|
| 3561 |
+
- bnb_4bit_use_double_quant: False
|
| 3562 |
+
- bnb_4bit_compute_dtype: float32
|
| 3563 |
+
|
| 3564 |
+
### Framework versions
|
| 3565 |
+
|
| 3566 |
+
|
| 3567 |
- 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:dce1e44d8ec8a71315f68a7b7b1dfd5762d09909df56d7f8a1a1d4073a0a08c7
|
| 3 |
size 21020682
|