Isabelle Cudlitz
commited on
Commit
·
404819b
1
Parent(s):
d61c783
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1440,4 +1440,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1440 |
### Framework versions
|
| 1441 |
|
| 1442 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1443 |
- PEFT 0.6.2
|
|
|
|
| 1440 |
### Framework versions
|
| 1441 |
|
| 1442 |
|
| 1443 |
+
- PEFT 0.6.2
|
| 1444 |
+
## Training procedure
|
| 1445 |
+
|
| 1446 |
+
|
| 1447 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1448 |
+
- load_in_8bit: False
|
| 1449 |
+
- load_in_4bit: True
|
| 1450 |
+
- llm_int8_threshold: 6.0
|
| 1451 |
+
- llm_int8_skip_modules: None
|
| 1452 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1453 |
+
- llm_int8_has_fp16_weight: False
|
| 1454 |
+
- bnb_4bit_quant_type: fp4
|
| 1455 |
+
- bnb_4bit_use_double_quant: True
|
| 1456 |
+
- bnb_4bit_compute_dtype: float32
|
| 1457 |
+
|
| 1458 |
+
### Framework versions
|
| 1459 |
+
|
| 1460 |
+
|
| 1461 |
- 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 sha256:49e756b492943c5fb514ad3565efba5b0cedd47aeb90cc6ef17d9079b58a00b9
|
| 3 |
size 21020682
|