Isabelle Cudlitz
commited on
Commit
·
5c1a735
1
Parent(s):
0b3c865
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4500,4 +4500,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 4500 |
### Framework versions
|
| 4501 |
|
| 4502 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4503 |
- PEFT 0.6.2
|
|
|
|
| 4500 |
### Framework versions
|
| 4501 |
|
| 4502 |
|
| 4503 |
+
- PEFT 0.6.2
|
| 4504 |
+
## Training procedure
|
| 4505 |
+
|
| 4506 |
+
|
| 4507 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4508 |
+
- load_in_8bit: True
|
| 4509 |
+
- load_in_4bit: False
|
| 4510 |
+
- llm_int8_threshold: 6.0
|
| 4511 |
+
- llm_int8_skip_modules: None
|
| 4512 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4513 |
+
- llm_int8_has_fp16_weight: False
|
| 4514 |
+
- bnb_4bit_quant_type: fp4
|
| 4515 |
+
- bnb_4bit_use_double_quant: False
|
| 4516 |
+
- bnb_4bit_compute_dtype: float32
|
| 4517 |
+
|
| 4518 |
+
### Framework versions
|
| 4519 |
+
|
| 4520 |
+
|
| 4521 |
- 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 sha256:7b72b8d7613c6b05a3e049dfdea22444aee3f0307e4f33290ee36a3fe956727a
|
| 3 |
size 21020682
|