Instructions to use cong1230/LDCC_LoRA_r16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cong1230/LDCC_LoRA_r16 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LDCC/LDCC-Instruct-Llama-2-ko-13B-v1.4") model = PeftModel.from_pretrained(base_model, "cong1230/LDCC_LoRA_r16") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- adapter_config.json +1 -1
- adapter_model.bin +1 -1
adapter_config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"init_lora_weights": true,
|
| 8 |
"layers_pattern": null,
|
| 9 |
"layers_to_transform": null,
|
| 10 |
-
"lora_alpha":
|
| 11 |
"lora_dropout": 0.1,
|
| 12 |
"modules_to_save": null,
|
| 13 |
"peft_type": "LORA",
|
|
|
|
| 7 |
"init_lora_weights": true,
|
| 8 |
"layers_pattern": null,
|
| 9 |
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 8,
|
| 11 |
"lora_dropout": 0.1,
|
| 12 |
"modules_to_save": null,
|
| 13 |
"peft_type": "LORA",
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 52486477
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ede57f726462fd409744d628ac4eb4edd4e878aeaecbbee620ed5b618b06e8
|
| 3 |
size 52486477
|