Update README.md

README.md

@@ -27,7 +27,7 @@ This model is trained on 350B tokens of English FineWeb V1.1.0 data and is not i
 
   [GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2](https://huggingface.co/ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.seed2)
 
-  [GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3](https://huggingface.co/ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3) 
+  [GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1](https://huggingface.co/ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1) 
 
   [GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3](https://huggingface.co/ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.seed3)
 
@@ -37,7 +37,7 @@ This model is trained on 350B tokens of English FineWeb V1.1.0 data and is not i
   
 **Generation**: 
 
-This is a simple example of how to use `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1` model.
+This is a simple example of how to use `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3` model.
 
 Install the following libraries:
 
@@ -51,7 +51,7 @@ Then, copy the code snippet below to run the example.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "auto"
-model_path = "ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1"
+model_path = "ibm-granite/GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 # drop device_map if running on CPU
 model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
@@ -74,6 +74,6 @@ print(output)
 
 **Infrastructure**: Please refer to section 5.2 of the [GneissWeb](https://arxiv.org/pdf/2502.14907) paper.
 
-**Ethical Considerations and Limitations**: The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1` is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed1` model with ethical intentions and in a responsible way.
+**Ethical Considerations and Limitations**: The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3` is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use `GneissWeb.7B_ablation_model_on_350B_FineWeb.Edu.seed3` model with ethical intentions and in a responsible way.
 
 **Resources**: Learn more about GneissWeb [here](https://huggingface.co/datasets/ibm-granite/GneissWeb).