up

README.md

@@ -19,7 +19,7 @@ inference: false
 
 # Vigogne-LoRA-7b: A French Instruct LLaMA Model
 
-Vigogne-LoRA-7b is a [LLaMA-7B](https://huggingface.co/decapoda-research/llama-7b-hf) model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇫🇷 French instructions.
+Vigogne-LoRA-7b is a LLaMA-7B model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇫🇷 French instructions.
 
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
 
@@ -33,13 +33,16 @@ This repo only contains the low-rank adapter. In order to access the complete mo
 from peft import PeftModel
 from transformers import LlamaForCausalLM, LlamaTokenizer
 
-tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
+base_model_name_or_path = "<name/or/path/to/hf/llama/7b/model>"
+lora_model_name_or_path = "bofenghuang/vigogne-lora-7b"
+
+tokenizer = LlamaTokenizer.from_pretrained(base_model_name_or_path)
 model = LlamaForCausalLM.from_pretrained(
-    "decapoda-research/llama-7b-hf",
+    base_model_name_or_path,
     load_in_8bit=True,
     device_map="auto",
 )
-model = PeftModel.from_pretrained(model, "bofenghuang/vigogne-lora-7b")
+model = PeftModel.from_pretrained(model, lora_model_name_or_path)
 ```
 
 You can infer this model by using the following Google Colab Notebook.

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723