Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: unsloth/Qwen3-14B-Base-unsloth-bnb-4bit
+base_model: unsloth/Qwen3-7b-Base-unsloth-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
@@ -17,7 +17,7 @@ pipeline_tag: text-generation
 library_name: transformers
 ---
 
-# 🦊 Riko-Qwen3-14B: Tsundere Kitsune AI
+# 🦊 Riko-Qwen3-7b: Tsundere Kitsune AI
 
 <div align="center">
   <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>
@@ -25,16 +25,16 @@ library_name: transformers
 
 ## 📋 Model Overview
 
-**Riko-Qwen3-14B** is a specialized conversational AI model fine-tuned to embody the personality of Riko, a tsundere kitsune character. Part of **Project Horizon LLM**, this model was trained using alternating responses from Kimi K2 and Horizon Beta, built on the robust Qwen3-14B foundation, delivering engaging, personality-driven conversations with authentic tsundere characteristics.
+**Riko-Qwen3-7b** is a specialized conversational AI model fine-tuned to embody the personality of Riko, a tsundere kitsune character. Part of **Project Horizon LLM**, this model was trained using alternating responses from Kimi K2 and Horizon Beta, built on the robust Qwen3-7b foundation, delivering engaging, personality-driven conversations with authentic tsundere characteristics.
 
-- **Base Model:** unsloth/Qwen3-14B-Base-unsloth-bnb-4bit
+- **Base Model:** unsloth/Qwen3-7b-Base-unsloth-bnb-4bit
 - **Source Models:** Kimi K2 + Horizon Beta (alternating turns)
 - **Project:** Project Horizon LLM
 - **Developer:** subsectmusic  
 - **Training Framework:** Unsloth + Hugging Face TRL
 - **Training Speed:** 2x faster optimization via Unsloth
 - **License:** Apache 2.0
-- **Model Size:** 14B parameters (4-bit quantized)
+- **Model Size:** 7b parameters (4-bit quantized)
 - **Format Support:** GGUF compatible for Ollama deployment
 
 ## 🎭 Character Profile: Riko
@@ -55,7 +55,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 # Load model and tokenizer
-model_name = "subsectmusic/riko-qwen3-14b"
+model_name = "subsectmusic/riko-qwen3-7b"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -68,10 +68,10 @@ model = AutoModelForCausalLM.from_pretrained(
 
 ```bash
 # Pull the GGUF model for Ollama
-ollama pull subsectmusic/riko-qwen3-14b
+ollama pull subsectmusic/riko-qwen3-7b
 
 # Start chatting with Riko
-ollama run subsectmusic/riko-qwen3-14b
+ollama run subsectmusic/riko-qwen3-7b
 ```
 
 ### Conversation Template
@@ -114,7 +114,7 @@ print(f"Riko: {response}")
 - **Creative Writing:** Generate authentic tsundere character dialogue and interactions
 - **Chatbot Applications:** Personality-driven AI assistant with character consistency
 - **Entertainment:** Fun, character-consistent interactions with kitsune AI personality
-- **Research:** Study knowledge distillation from larger models (Kimi K2 → Qwen3-14B)
+- **Research:** Study knowledge distillation from larger models (Kimi K2 → Qwen3-7b)
 - **Educational:** Understanding Project Horizon LLM methodology and alternating training approaches
 
 ## 🔬 Project Horizon LLM Methodology
@@ -125,7 +125,7 @@ print(f"Riko: {response}")
 - **Source Models:** 
   - **Kimi K2** (Turn 1, 3, 5... responses)
   - **Horizon Beta** (Turn 2, 4, 6... responses) - OpenRouter's cloaked model (#2 Translation, #3 Programming)
-- **Target Model:** Qwen3-14B (student model) 
+- **Target Model:** Qwen3-7b (student model) 
 - **Knowledge Transfer:** Personality traits and response patterns from both high-quality models
 - **Character Focus:** Specialized curation for tsundere kitsune personality (Riko)
 
@@ -138,7 +138,7 @@ The training methodology involves:
 4. **Alternating Pattern:** Continue alternating between Kimi K2 and Horizon Beta for each turn
 5. **Response Curation:** Select and refine responses that best match Riko's tsundere personality
 6. **Dataset Compilation:** Combine curated human queries with personality-matched responses
-7. **Fine-tuning:** Train Qwen3-14B on the curated dataset using Unsloth + TRL
+7. **Fine-tuning:** Train Qwen3-7b on the curated dataset using Unsloth + TRL
 
 This approach ensures:
 - **Personality Consistency:** Responses align with Riko's tsundere kitsune character
@@ -181,7 +181,7 @@ Sequence Length: Dynamic (up to context limit)
 | Attribute | Details |
 |-----------|---------|
 | Architecture | Qwen3 Transformer |
-| Parameters | 14B (4-bit quantized) |
+| Parameters | 7b (4-bit quantized) |
 | Source Models | Kimi K2 + Horizon Beta (alternating) |
 | Project | Project Horizon LLM |
 | Context Length | Model dependent |