Isabelle Cudlitz
commited on
Commit
·
72d171a
1
Parent(s):
f37e5cf
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1566,4 +1566,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1566 |
### Framework versions
|
| 1567 |
|
| 1568 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1569 |
- PEFT 0.6.2
|
|
|
|
| 1566 |
### Framework versions
|
| 1567 |
|
| 1568 |
|
| 1569 |
+
- PEFT 0.6.2
|
| 1570 |
+
## Training procedure
|
| 1571 |
+
|
| 1572 |
+
|
| 1573 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1574 |
+
- load_in_8bit: True
|
| 1575 |
+
- load_in_4bit: False
|
| 1576 |
+
- llm_int8_threshold: 6.0
|
| 1577 |
+
- llm_int8_skip_modules: None
|
| 1578 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1579 |
+
- llm_int8_has_fp16_weight: False
|
| 1580 |
+
- bnb_4bit_quant_type: fp4
|
| 1581 |
+
- bnb_4bit_use_double_quant: False
|
| 1582 |
+
- bnb_4bit_compute_dtype: float32
|
| 1583 |
+
|
| 1584 |
+
### Framework versions
|
| 1585 |
+
|
| 1586 |
+
|
| 1587 |
- 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 sha256:4f3a71d3b379686cabed63755bbc00894ee959916bf43bec9e2cbcb9c1649a90
|
| 3 |
size 21020682
|