Isabelle Cudlitz
commited on
Commit
·
94dbb5e
1
Parent(s):
bea25b0
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1458,4 +1458,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1458 |
### Framework versions
|
| 1459 |
|
| 1460 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1461 |
- PEFT 0.6.2
|
|
|
|
| 1458 |
### Framework versions
|
| 1459 |
|
| 1460 |
|
| 1461 |
+
- PEFT 0.6.2
|
| 1462 |
+
## Training procedure
|
| 1463 |
+
|
| 1464 |
+
|
| 1465 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1466 |
+
- load_in_8bit: True
|
| 1467 |
+
- load_in_4bit: False
|
| 1468 |
+
- llm_int8_threshold: 6.0
|
| 1469 |
+
- llm_int8_skip_modules: None
|
| 1470 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1471 |
+
- llm_int8_has_fp16_weight: False
|
| 1472 |
+
- bnb_4bit_quant_type: fp4
|
| 1473 |
+
- bnb_4bit_use_double_quant: False
|
| 1474 |
+
- bnb_4bit_compute_dtype: float32
|
| 1475 |
+
|
| 1476 |
+
### Framework versions
|
| 1477 |
+
|
| 1478 |
+
|
| 1479 |
- 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:f066470de05791517c6e6036aa46919a5f7bff44fc0a52738964bd77a81b90e3
|
| 3 |
size 21020682
|