Update README.md

README.md

@@ -4,6 +4,15 @@ tags:
 - unsloth
 - trl
 - sft
+license: apache-2.0
+datasets:
+- Anudeep28/game-theory-dataset
+language:
+- en
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+new_version: Anudeep28/DeepSeek-R1-Distill-Llama-8B-Game-theory-V1
+pipeline_tag: text2text-generation
 ---
 
 # Model Card for Model ID
@@ -12,21 +21,99 @@ tags:
 
 
 
-## Model Details
+# DeepSeek-GT: Game Theory Specialized Language Model
+
+## Model Description
+DeepSeek-GT is a fine-tuned version of the DeepSeek Coder Instruct 8B model, specifically optimized for game theory analysis and problem-solving. Built on the efficient DeepSeek-R1-Distill-Llama-8B architecture, this model has been trained on a curated dataset of real-world game theory scenarios, strategic analyses, and solutions.
 
-### Model Description
+## Key Features
+- **Specialized Knowledge**: Fine-tuned on diverse game theory examples, including Nash Equilibrium analysis, strategic decision-making, and payoff evaluations
+- **Structured Reasoning**: Provides step-by-step analysis of game theory real life scenarios, breaking down complex strategic situations into comprehensible components
+- **Solution-Oriented**: Generates detailed solutions with clear reasoning paths and strategic implications
+- **Architecture**: Based on DeepSeek's 8B parameter model, offering a balance between performance and computational efficiency
 
+## Use Cases
+- Analyzing strategic interactions in business and economics
+- Solving game theory problems with detailed explanations
+- Understanding Nash Equilibria in various scenarios
+- Evaluating payoff matrices and optimal strategies
+- Providing insights for decision-making in competitive situations
+
+## Model Details
+- **Base Model**: DeepSeek-R1-Distill-Llama-8B
+- **Training Data**: Curated dataset of game theory examples and solutions
+- **Input Format**: Accepts scenario descriptions and questions about real life situations
+- **Output Format**: Structured responses including scenario analysis, strategic reasoning, and solutions
+
+## Example Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+# Define a system prompt under prompt_style 
+prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context. 
+Write a response that appropriately completes the request. 
+Before answering, think carefully about the Scenario and create a step-by-step chain of thoughts to ensure a logical and accurate response.
+
+### Instruction:
+You are a Game theory expert with advanced knowledge in Game theory reasoning, solutions, and in finding the optimized output. 
+Please answer the following Game theory related Scenario. 
+
+### Scenario:
+{}
+"""
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from unsloth import FastLanguageModel
+import torch
+
+# Load model and tokenizer from hub
+model = AutoModelForCausalLM.from_pretrained(
+    "Anudeep28/DeepSeek-R1-Distill-Llama-8B-Game-theory-V1",  # your model repository name
+    torch_dtype=torch.float16,      # use float16 for efficiency
+    device_map="auto",
+    load_in_4bit=True           # automatically handle device placement
+)
+tokenizer = AutoTokenizer.from_pretrained("Anudeep28/DeepSeek-R1-Distill-Llama-8B-Game-theory-V1")
+
+# Optional: Use Unsloth's optimization if you want the faster inference
+
+FastLanguageModel.for_inference(model)
+
+# Prepare your prompt
+question = """Chris and Kim are attending the same conference and want to meet. 
+            They can choose between swimming and hiking, but they don't know each other's choice beforehand. 
+            They both prefer swimming, but only if they are together."""
+
+# Load the inference model using FastLanguageModel (Unsloth optimizes for speed)
+# merged_model = merged_model.cuda()
+# FastLanguageModel.for_inference(merged_model)  # Unsloth has 2x faster inference!
+
+# Tokenize the input question with a specific prompt format and move it to the GPU
+inputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda")
+
+# Tokenize input
+# Generate a response using LoRA fine-tuned model with specific parameters
+outputs = model.generate(
+    input_ids=inputs.input_ids,          # Tokenized input IDs
+    attention_mask=inputs.attention_mask, # Attention mask for padding handling
+    max_new_tokens=1200,                  # Maximum length for generated response
+    use_cache=True,                        # Enable cache for efficient generation
+)
+
+# Decode the generated response from tokenized format to readable text
+response = tokenizer.batch_decode(outputs)
+
+# Extract and print only the model's response part after "### Response:"
+print(response[0].split("### Response:")[1])
 <!-- Provide a longer summary of what this model is. -->
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** [Eneru]
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Finetuned from model [deepseek-ai/DeepSeek-R1-Distill-Llama-8B]:** [More Information Needed]
 
 ### Model Sources [optional]