Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1548,4 +1548,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1548 |
### Framework versions
|
| 1549 |
|
| 1550 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1551 |
- PEFT 0.6.2
|
|
|
|
| 1548 |
### Framework versions
|
| 1549 |
|
| 1550 |
|
| 1551 |
+
- PEFT 0.6.2
|
| 1552 |
+
## Training procedure
|
| 1553 |
+
|
| 1554 |
+
|
| 1555 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1556 |
+
- load_in_8bit: False
|
| 1557 |
+
- load_in_4bit: True
|
| 1558 |
+
- llm_int8_threshold: 6.0
|
| 1559 |
+
- llm_int8_skip_modules: None
|
| 1560 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1561 |
+
- llm_int8_has_fp16_weight: False
|
| 1562 |
+
- bnb_4bit_quant_type: fp4
|
| 1563 |
+
- bnb_4bit_use_double_quant: True
|
| 1564 |
+
- bnb_4bit_compute_dtype: float32
|
| 1565 |
+
|
| 1566 |
+
### Framework versions
|
| 1567 |
+
|
| 1568 |
+
|
| 1569 |
- 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 sha256:06fbb9810d416b3180460fc2c73e4ad0816df26eb0bc4bccf8a45ea5b046f555
|
| 3 |
size 21020682
|