Update model card

README.md

@@ -1,51 +1,59 @@
 ---
 language: en
-license: apache-2.0
 tags:
-- mathematics
-- chain-of-thought
-- question-answering
+- arxiv
+- research-papers
+- text-generation
+license: apache-2.0
 ---
 
-# KnullAI v2 - Fine-tuned on GAIR/o1-journey
+# KnullAI v2 - Fine-tuned on ArXiver Dataset
 
-This model is a fine-tuned version of KnullAI v2, specifically trained on mathematical problem-solving using the GAIR/o1-journey dataset.
+This model is a fine-tuned version of KnullAI v2, specifically trained on the ArXiver dataset containing research paper information.
 
 ## Training Data
-The model was fine-tuned on the GAIR/o1-journey dataset, which contains:
-- Mathematical questions
-- Detailed answers
-- Step-by-step explanations (Chain of Thought)
+The model was fine-tuned on the neuralwork/arxiver dataset, which contains:
+- Paper titles
+- Abstracts
+- Authors
+- Publication dates
+- Links
+
+## Model Details
+- Base model: Rawkney/knullAi_v2
+- Training type: Causal language modeling
+- Hardware: T4 GPU
+- Mixed precision: FP16
 
 ## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("Rawkney/knullAi_v2")
-tokenizer = AutoTokenizer.from_pretrained("Rawkney/knullAi_v2")
+model = AutoModelForCausalLM.from_pretrained("YOUR_REPO_ID")
+tokenizer = AutoTokenizer.from_pretrained("YOUR_REPO_ID")
 
 # Example usage
-question = "What is the area of a triangle with vertices at (0,0), (3,0), and (0,4)?"
-input_text = f"Question: {question}\nAnswer:"
-inputs = tokenizer(input_text, return_tensors="pt")
+title = "Your paper title"
+input_text = f"Title: {title}\nAbstract:"
+inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
 
 outputs = model.generate(
     inputs["input_ids"],
-    max_length=512,
+    max_length=256,
     temperature=0.7,
-    top_p=0.9
+    top_p=0.9,
+    pad_token_id=tokenizer.eos_token_id
 )
 
 response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(response)
 ```
 
-## Training Procedure
-- Fine-tuned using the Transformers library
-- Training parameters:
-  - Learning rate: 2e-5
-  - Epochs: 3
-  - Batch size: 2
-  - Gradient accumulation steps: 4
-  - Mixed precision training (fp16)
+## Training Parameters
+- Learning rate: 1e-5
+- Epochs: 1
+- Batch size: 1
+- Gradient accumulation steps: 16
+- Mixed precision training (fp16)
+- Max sequence length: 512