Instructions to use minhchuxuan/llama-2.7b-dolly-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use minhchuxuan/llama-2.7b-dolly-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/LMOps/minillm/checkpoints/Sheared-LLaMA-2.7B-Pruned/") model = PeftModel.from_pretrained(base_model, "minhchuxuan/llama-2.7b-dolly-lora") - Notebooks
- Google Colab
- Kaggle
Upload adapter_model.bin with huggingface_hub
Browse files- adapter_model.bin +3 -0
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a0432fb286b22e01d824a486a6cbe8ba3364a59f630914686ca8661c2d9564
|
| 3 |
+
size 10506963
|