Upload folder using huggingface_hub
Browse files- README.md +13 -0
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -4,6 +4,18 @@ library_name: peft
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- quant_method: bitsandbytes
|
9 |
- load_in_8bit: True
|
@@ -17,5 +29,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
17 |
- bnb_4bit_compute_dtype: float32
|
18 |
### Framework versions
|
19 |
|
|
|
20 |
|
21 |
- PEFT 0.5.0
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: True
|
10 |
+
- load_in_4bit: False
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
|
19 |
The following `bitsandbytes` quantization config was used during training:
|
20 |
- quant_method: bitsandbytes
|
21 |
- load_in_8bit: True
|
|
|
29 |
- bnb_4bit_compute_dtype: float32
|
30 |
### Framework versions
|
31 |
|
32 |
+
- PEFT 0.5.0
|
33 |
|
34 |
- PEFT 0.5.0
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13677706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d3a149e6d805d10d2030fdf79b20f34c1556a22bb667c88f4a7d5e4a662c6cd
|
3 |
size 13677706
|