Commit
•
54bf157
1
Parent(s):
0b5152d
Upload folder using huggingface_hub
Browse files- README.md +12 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -4,6 +4,17 @@ library_name: peft
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
- load_in_8bit: False
|
| 9 |
- load_in_4bit: True
|
|
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 16 |
- bnb_4bit_compute_dtype: bfloat16
|
| 17 |
### Framework versions
|
| 18 |
|
|
|
|
| 19 |
|
| 20 |
- PEFT 0.4.0
|
|
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- load_in_8bit: False
|
| 9 |
+
- load_in_4bit: True
|
| 10 |
+
- llm_int8_threshold: 6.0
|
| 11 |
+
- llm_int8_skip_modules: None
|
| 12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
+
- llm_int8_has_fp16_weight: False
|
| 14 |
+
- bnb_4bit_quant_type: nf4
|
| 15 |
+
- bnb_4bit_use_double_quant: True
|
| 16 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 17 |
+
|
| 18 |
The following `bitsandbytes` quantization config was used during training:
|
| 19 |
- load_in_8bit: False
|
| 20 |
- load_in_4bit: True
|
|
|
|
| 27 |
- bnb_4bit_compute_dtype: bfloat16
|
| 28 |
### Framework versions
|
| 29 |
|
| 30 |
+
- PEFT 0.4.0
|
| 31 |
|
| 32 |
- PEFT 0.4.0
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50402250
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67078c434e8a0eb8dc11b777a2ca7a64e0f3e2ce7dc22793e593f60a3e3681bb
|
| 3 |
size 50402250
|