Isabelle Cudlitz commited on
Commit ·
e122809
1
Parent(s): 56a00ed
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1476,4 +1476,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1476 |
### Framework versions
|
| 1477 |
|
| 1478 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1479 |
- PEFT 0.6.2
|
|
|
|
| 1476 |
### Framework versions
|
| 1477 |
|
| 1478 |
|
| 1479 |
+
- PEFT 0.6.2
|
| 1480 |
+
## Training procedure
|
| 1481 |
+
|
| 1482 |
+
|
| 1483 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1484 |
+
- load_in_8bit: False
|
| 1485 |
+
- load_in_4bit: True
|
| 1486 |
+
- llm_int8_threshold: 6.0
|
| 1487 |
+
- llm_int8_skip_modules: None
|
| 1488 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1489 |
+
- llm_int8_has_fp16_weight: False
|
| 1490 |
+
- bnb_4bit_quant_type: fp4
|
| 1491 |
+
- bnb_4bit_use_double_quant: True
|
| 1492 |
+
- bnb_4bit_compute_dtype: float32
|
| 1493 |
+
|
| 1494 |
+
### Framework versions
|
| 1495 |
+
|
| 1496 |
+
|
| 1497 |
- 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 sha256:70bf9e0a540239097a90fed58fee54a4a0a6ed4f09b4ac01635761a581dbee84
|
| 3 |
size 21020682
|