diff --git a/inference/README.md b/inference/README.md
index c7d58f68a..9edbe83fe 100644
--- a/inference/README.md
+++ b/inference/README.md
@@ -22,7 +22,7 @@ conda activate gorilla
 pip install -r requirements.txt
 ```
 
-We release the weights for [`gorilla-mpt-7b-hf-v0`](https://huggingface.co/gorilla-llm/gorilla-mpt-7b-hf-delta-v0) and [`gorilla-falcon-7b-hf-v0`](https://huggingface.co/gorilla-llm/gorilla-falcon-7b-hf-delta-v0) on Huggingface. You can directly download them! For the llama-finetuned models we release the weights as a delta to be compliant with the LLaMA model license. You can apply the delta weights using the following commands below: 
+We release the weights for [`gorilla-mpt-7b-hf-v0`](https://huggingface.co/gorilla-llm/gorilla-mpt-7b-hf-v0) and [`gorilla-falcon-7b-hf-v0`](https://huggingface.co/gorilla-llm/gorilla-falcon-7b-hf-v0) on Huggingface. You can directly download them! For the llama-finetuned models we release the weights as a delta to be compliant with the LLaMA model license. You can apply the delta weights using the following commands below: 
 
 ### Downloading Gorilla Delta Weights
 
@@ -58,7 +58,7 @@ python3 serve/gorilla_falcon_cli.py --model-path path/to/gorilla-falcon-7b-hf-v0
 
 ### [Optional] Batch Inference on a Prompt File
 
-After downloading the model, you need to make a jsonl file containing all the question you want to inference through Gorilla. Here is [one example](https://github.com/ShishirPatil/gorilla/tree/main/inference/questions/example.jsonl): 
+After downloading the model, you need to make a jsonl file containing all the question you want to inference through Gorilla. Here is [one example](https://github.com/ShishirPatil/gorilla/blob/main/inference/example_questions/example_questions.jsonl): 
 
 ```
 {"question_id": 1, "text": "I want to generate image from text."}