Update README.md

README.md

@@ -15,7 +15,8 @@ A 60M parameter language model trained on `22 * 60M` tokens from FineWeb-Edu dat
 
 ## Model Details
 
-aixsim-60M is a transformer-based language model with approximately 60 million parameters (embedding layer params excluded). It uses RMSNorm for normalization and is trained on the FineWeb dataset.
+aixsim-60M is a transformer-based language model with approximately 60 million parameters (embedding layer params excluded). 
+It uses RMSNorm for normalization and is trained on the FineWeb-Edu dataset.
 
 - **Developed by:** AICrossSim
 - **Funded by:** [ARIA](https://www.aria.org.uk/)
@@ -34,7 +35,7 @@ Experiment setup and training logs can be found at [wandb run](https://wandb.ai/
 import transformers
 
 model_name="AICrossSim/clm-60m"
-model = transformers.AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=getattr(torch, dtype))
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
 ```