Update README.md

README.md

@@ -11,12 +11,12 @@ pipeline_tag: text-generation
 
 # gpt2-xl-camel-ai-physics (1.5B)
 
-**lgaalves/gpt2-xl-camel-ai-physics** is an instruction fine-tuned model based on the GPT-2 transformer architecture.
+**lgaalves/gpt2-xl_camel-ai-physics** is an instruction fine-tuned model based on the GPT-2 transformer architecture.
 
 
 ### Benchmark Metrics
 
-| Metric                |lgaalves/gpt2-xl-camel-ai-physics |gpt2-xl (base) |
+| Metric                |lgaalves/gpt2-xl_camel-ai-physics |gpt2-xl (base) |
 |-----------------------|-------|-------|
 | Avg.                  | 36.51 | **36.66** |
 | ARC (25-shot)         | 29.52 | **30.29** |
@@ -30,7 +30,7 @@ We use state-of-the-art [Language Model Evaluation Harness](https://github.com/E
 ### Model Details
 
 * **Trained by**: Luiz G A Alves
-* **Model type:**  **lgaalves/gpt2-xl-camel-ai-physics** is an auto-regressive language model based on the GPT-2 transformer architecture.
+* **Model type:**  **lgaalves/gpt2-xl_camel-ai-physics** is an auto-regressive language model based on the GPT-2 transformer architecture.
 * **Language(s)**: English
 
 ### How to use:
@@ -38,7 +38,7 @@ We use state-of-the-art [Language Model Evaluation Harness](https://github.com/E
 ```python
 # Use a pipeline as a high-level helper
 >>> from transformers import pipeline
->>> pipe = pipeline("text-generation", model="lgaalves/gpt2-xl-camel-ai-physics")
+>>> pipe = pipeline("text-generation", model="lgaalves/gpt2-xl_camel-ai-physics")
 >>> question = "What is a large language model?"
 >>> answer = pipe(question)
 >>> print(answer[0]['generated_text'])
@@ -51,17 +51,17 @@ or, you can load the model direclty using:
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2-xl-camel-ai-physics")
-model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2-xl-camel-ai-physics")
+tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2-xl_camel-ai-physics")
+model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2-xl_camel-ai-physics")
 ```
 
 ### Training Dataset
 
-`lgaalves/gpt2-xl-camel-ai-physics` trained on the GPT4 generated dataset [lgaalves/camel-physics](https://huggingface.co/datasets/lgaalves/camel-physics).
+`lgaalves/gpt2-xl_camel-ai-physics` trained on the GPT4 generated dataset [lgaalves/camel-physics](https://huggingface.co/datasets/lgaalves/camel-physics).
 
 ### Training Procedure
 
-`lgaalves/gpt2-xl-camel-ai-physics` was instruction fine-tuned using LoRA on  1 Tesla V100-SXM2-16GB. It took about 3 hours to train it.  
+`lgaalves/gpt2-xl_camel-ai-physics` was instruction fine-tuned using LoRA on  1 Tesla V100-SXM2-16GB. It took about 3 hours to train it.  
 
 
 # Intended uses, limitations & biases