Isabelle Cudlitz
commited on
Commit
·
c2d32af
1
Parent(s):
94467ee
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2700,4 +2700,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2700 |
### Framework versions
|
| 2701 |
|
| 2702 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2703 |
- PEFT 0.6.2
|
|
|
|
| 2700 |
### Framework versions
|
| 2701 |
|
| 2702 |
|
| 2703 |
+
- PEFT 0.6.2
|
| 2704 |
+
## Training procedure
|
| 2705 |
+
|
| 2706 |
+
|
| 2707 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2708 |
+
- load_in_8bit: True
|
| 2709 |
+
- load_in_4bit: False
|
| 2710 |
+
- llm_int8_threshold: 6.0
|
| 2711 |
+
- llm_int8_skip_modules: None
|
| 2712 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2713 |
+
- llm_int8_has_fp16_weight: False
|
| 2714 |
+
- bnb_4bit_quant_type: fp4
|
| 2715 |
+
- bnb_4bit_use_double_quant: False
|
| 2716 |
+
- bnb_4bit_compute_dtype: float32
|
| 2717 |
+
|
| 2718 |
+
### Framework versions
|
| 2719 |
+
|
| 2720 |
+
|
| 2721 |
- 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 sha256:33401a108e61cf51f693b85bac7fedf34d5ad5838f8463c6c5f050ce305387c0
|
| 3 |
size 21020682
|