Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3528,4 +3528,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3528 |
### Framework versions
|
| 3529 |
|
| 3530 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3531 |
- PEFT 0.6.2
|
|
|
|
| 3528 |
### Framework versions
|
| 3529 |
|
| 3530 |
|
| 3531 |
+
- PEFT 0.6.2
|
| 3532 |
+
## Training procedure
|
| 3533 |
+
|
| 3534 |
+
|
| 3535 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3536 |
+
- load_in_8bit: True
|
| 3537 |
+
- load_in_4bit: False
|
| 3538 |
+
- llm_int8_threshold: 6.0
|
| 3539 |
+
- llm_int8_skip_modules: None
|
| 3540 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3541 |
+
- llm_int8_has_fp16_weight: False
|
| 3542 |
+
- bnb_4bit_quant_type: fp4
|
| 3543 |
+
- bnb_4bit_use_double_quant: False
|
| 3544 |
+
- bnb_4bit_compute_dtype: float32
|
| 3545 |
+
|
| 3546 |
+
### Framework versions
|
| 3547 |
+
|
| 3548 |
+
|
| 3549 |
- 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 sha256:97f03b4ca9219338fb867c5cf17904d41d93d95a388521e75d7b57a29cbc75db
|
| 3 |
size 21020682
|