Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3438,4 +3438,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3438 |
### Framework versions
|
| 3439 |
|
| 3440 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3441 |
- PEFT 0.6.2
|
|
|
|
| 3438 |
### Framework versions
|
| 3439 |
|
| 3440 |
|
| 3441 |
+
- PEFT 0.6.2
|
| 3442 |
+
## Training procedure
|
| 3443 |
+
|
| 3444 |
+
|
| 3445 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3446 |
+
- load_in_8bit: True
|
| 3447 |
+
- load_in_4bit: False
|
| 3448 |
+
- llm_int8_threshold: 6.0
|
| 3449 |
+
- llm_int8_skip_modules: None
|
| 3450 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3451 |
+
- llm_int8_has_fp16_weight: False
|
| 3452 |
+
- bnb_4bit_quant_type: fp4
|
| 3453 |
+
- bnb_4bit_use_double_quant: False
|
| 3454 |
+
- bnb_4bit_compute_dtype: float32
|
| 3455 |
+
|
| 3456 |
+
### Framework versions
|
| 3457 |
+
|
| 3458 |
+
|
| 3459 |
- 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 sha256:6f6efacc50b26ef8bb833adf92319a54b2d5a1d81f9b9187655f30f7788eea72
|
| 3 |
size 21020682
|