--- library_name: transformers 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 # 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. ## 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]) 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:** [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 [deepseek-ai/DeepSeek-R1-Distill-Llama-8B]:** [More Information Needed] ### Model Sources [optional] - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses ### Direct Use [More Information Needed] ### Downstream Use [optional] [More Information Needed] ### Out-of-Scope Use [More Information Needed] ## Bias, Risks, and Limitations [More Information Needed] ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data [More Information Needed] ### Training Procedure #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] #### Speeds, Sizes, Times [optional] [More Information Needed] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data [More Information Needed] #### Factors [More Information Needed] #### Metrics [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] [More Information Needed] ## Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]