Update README.md

README.md

@@ -35,7 +35,7 @@ This model was built via parameter-efficient finetuning of the [meta-llama/Llama
 
 ## Model Sources 
 
-- **Repository:** [here](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/llama/sft_Llama_2_13b_chat_hf_v0_1_peft.ipynb)
+- **Repository:** [here](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/llama/sft_Llama_2_13B_Instruct_v0_2_peft.ipynb)
 
 ## Evaluation Results
 
@@ -202,7 +202,7 @@ print(tokenizer.decode(input_ids[0]))
 
 We use the [SFTTrainer](https://huggingface.co/docs/trl/main/en/sft_trainer) from `trl` to fine-tune LLMs on instruction-following datasets.
 
-See [here](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/mistral/sft_Mistral_7B_Instruct_v0_1_peft.ipynb) for the finetuning code, which contains an exhaustive view of the hyperparameters employed.
+See [here](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/llama/sft_Llama_2_13B_Instruct_v0_2_peft.ipynb) for the finetuning code, which contains an exhaustive view of the hyperparameters employed.
 
 The following `TrainingArguments` config was used: