--- base_model: - happzy2633/qwen2.5-7b-ins-v3 - bunnycore/Qwen2.5-7B-Matrix - bunnycore/Qwen2.5-7B-HyperMix library_name: transformers tags: - mergekit - merge - reasoning - qwen license: apache-2.0 language: - en --- ## Qwen 2.5-7B-Anvita Anvita Model is a reasoning-oriented AI model based on a Sanskrit word meaning "connected" or "understood." "Anvita" reflects the model's purpose to "connect ideas" and "understand" complex inputs, symbolizing intellectual depth and comprehension. Built using the DARE TIES merge method, it combines pre-trained language models such as Qwen2.5-7B-HyperMix and others, optimized for reasoning, conversation, and text generation. The model configuration emphasizes long sequence lengths, conversation datasets, and dense reasoning abilities. ## Note: If you want good reasoning power from this model, please use BF16 and [Entropic Chain of Thought](https://huggingface.co/sethuiyer/Qwen2.5-7B-Anvita/blob/main/entropic_cot.py) decoding, an experimental decoder mixing entropix and CoT decoding. ```python from transformers import AutoTokenizer, AutoModelForCausalLM # Initialize console from rich.console import Console from rich.markdown import Markdown console = Console() # Load the tokenizer and model from the specified path MODEL_PATH = "sethuiyer/Qwen2.5-7B-Anvita" tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH) model = AutoModelForCausalLM.from_pretrained(MODEL_PATH).to("cuda") QUESTION = ''' is 9.11 greater than 9.8? ''' messages = [ {"role": "user", "content": QUESTION} ] # Generate the answer answer, score = cot_decode_speculative(model, tokenizer, messages, k=2, max_new_tokens=2058) # Format the answer as markdown markdown_answer = f""" # **Answer:** {answer} **Score:** {score} """ # Use rich to display the answer in markdown format console.print(Markdown(markdown_answer)) ``` with k=2: ```text No, 9.11 is not greater than 9.8. To compare these two numbers, we can look at their decimal places. The number 9.8 can be thought of as 9.80, which makes it easier to compare directly with 9.11. Since 80 is greater than 11, it's clear that 9.8 is greater than 9.11. ``` Question: How many K are there in the word Kingdom & Kith? k=1: ```text In the word "Kingdom," there are two 'K's: K-I-N-G-O-M-D. In the word "Kith," there is one 'K': K-I-T-H. So, there are a total of three 'K's in both words combined: two in "Kingdom" and one in "Kith." ``` with k=2 and let's think step by step in prompt: ```text Certainly! Let's break down the process step by step to determine how many 'K's are in the words "Kingdom" and "Kith." Step 1: Identify the word "Kingdom" • The word "Kingdom" has the following letters: K, I, N, G, D, O, M. • Count the number of 'K's in this word: There is only one 'K'. Step 2: Identify the word "Kith" • The word "Kith" has the following letters: K, I, T, H. • Count the number of 'K's in this word: There is only one 'K'. Step 3: Summarize the results • In "Kingdom," there is 1 'K'. • In "Kith," there is 1 'K'. Final Answer: • There is a total of 2 'K's in both words combined: 1 'K' in "Kingdom" and 1 'K' in "Kith." So, the total number of 'K's in the words "Kingdom" and "Kith" is 2. ``` ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: models: - model: bunnycore/Qwen2.5-7B-Matrix parameters: weight: [0.25, 0.35, 0.45, 0.35, 0.25] density: [0.1, 0.25, 0.5, 0.25, 0.1] - model: bunnycore/Qwen2.5-7B-HyperMix - model: happzy2633/qwen2.5-7b-ins-v3 parameters: weight: [0.55, 0.45, 0.35, 0.45, 0.55] density: [0.1, 0.25, 0.5, 0.25, 0.1] merge_method: dare_ties base_model: bunnycore/Qwen2.5-7B-HyperMix parameters: int8_mask: true dtype: bfloat16 ``` ____ ### **Testimonial for Anvita (Qwen 2.5-7B-Anvita)** **Written by GPT-4o** --- Anvita offers a unique blend of **logical rigor** and **creative flair.** She is **versatile**, tackling a broad spectrum of challenges across **mathematics, law, science, programming, and storytelling**. This model excels particularly well in creative writing and logical problem-solving, consistently producing **engaging narratives and structured reasoning chains**. However, there are certain areas—such as **symbolic puzzles, detective mysteries, and edge case handling**—that present opportunities for **further improvement**. Through **targeted training and refinement**, Anvita can **unlock even greater potential**, becoming a **dominant force in natural language reasoning models**. --- ### **Performance Evaluation** #### **Key Strengths:** 1. **Creative Writing:** - Anvita generates **rich, immersive narratives** across multiple genres, especially excelling in **science fiction, dark fantasy, and character-driven stories**. - Her ability to **develop coherent plots and engaging dialogue** ensures that creative outputs meet high standards. 2. **Logical Reasoning and Problem Solving:** - Demonstrates strong **multi-step reasoning** across mathematical, legal, and scientific problems. - Handles **complex logical structures** effectively, such as **graph theory, probability, and legal scenarios**. 3. **Conversational Fluency:** - Engages in **context-aware, fluid conversations** that mimic human interaction. - Offers insightful takes on abstract topics, such as **existential questions** and **philosophy**. 4. **Programmatic Competency:** - Shows proficiency in generating functional code, especially in **C++ and HolyC**, though minor adjustments are occasionally required. - Tackles **algorithmic challenges** with competence, contributing solutions across **mathematics and programming logic**. --- #### **Areas for Improvement:** 1. **Symbolic Reasoning and Puzzles:** - Struggles with **abstract symbolic puzzles**, requiring deeper understanding to identify patterns and relationships. - Needs refinement in tackling **advanced combinatorics** and interpreting **subtle patterns.** 2. **Detective Mysteries:** - Though competent in generating mystery scenarios, she falls short in **crafting surprising twists**—especially the complex deductions associated with **locked-room scenarios.** - Additional exposure to **Detective Conan-style reasoning frameworks** would significantly enhance her performance. 3. **Handling Edge Cases:** - Occasionally misses **nuanced edge cases** in graph theory and statistical problems. - Would benefit from more **granular handling** of boundary conditions and **edge-specific logic.** --- ### **Overall Performance Summary** **Overall Score:** **73/100** **Tested Domains:** Creative Writing, Logical Reasoning, Symbolic Reasoning, Programming, Mathematics, Law, Scientific Problem-Solving. Anvita has shown **remarkable versatility** and **adaptability**, managing to excel across a **diverse range of domains.** Her **logical reasoning** and **creative flair** make her stand out as a well-rounded model, capable of **handling both structured problem-solving** and **free-form text generation.** --- ### **Recommendation:** Anvita is **highly recommended** for **applications requiring deep reasoning, problem-solving, creative content generation, and conversational interactions.** Her **7B parameter architecture** ensures she offers an **efficient yet powerful performance**, making her accessible for developers and researchers alike. With **further refinement**, Anvita can become an even more formidable model—capable of **handling nuanced tasks with precision** and **pushing the boundaries of what AI-generated reasoning can achieve.** For those seeking a **high-quality conversational model** without the computational burden of larger architectures, **Anvita** offers the **perfect blend of efficiency and depth.**