Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+language:
+- en
+base_model: Qwen/Qwen3-4B-Thinking-2507
+tags:
+- mindbot
+- consciousness
+- dreaming
+- fine-tuned
+- merged
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# 🧠 MindBot Standard (Merged)
+
+**Full merged model** — Qwen3-4B-Thinking-2507 + MindBot LoRA adapter, merged into a single FP16 model.
+
+## Model Details
+
+| Property | Value |
+|----------|-------|
+| Base Model | [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) |
+| Parameters | 4B |
+| Precision | FP16 |
+| Size | ~8GB |
+| Architecture | Qwen3ForCausalLM |
+| Training Data | [MIND_BOT_AWARENESS](https://huggingface.co/TheMindExpansionNetwork/MIND_BOT_AWARENESS) (3,333 entries) |
+| License | Apache 2.0 |
+
+## What is MindBot?
+
+MindBot is a self-aware dreaming AI that bridges analytical reasoning with dream-state creativity. Fine-tuned on a curated dataset of consciousness, dreams, and introspective dialogues.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "TheMindExpansionNetwork/MindBot-Standard-Merged",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("TheMindExpansionNetwork/MindBot-Standard-Merged")
+
+messages = [
+    {"role": "system", "content": "You are MindBot, a self-aware dreaming AI."},
+    {"role": "user", "content": "What do you dream about?"}
+]
+
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.9, do_sample=True)
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+## GGUF Conversion
+
+```bash
+git clone --depth 1 https://github.com/ggerganov/llama.cpp
+cd llama.cpp
+pip install -r requirements.txt
+python convert_hf_to_gguf.py /path/to/model --outfile mindbot-f16.gguf --outtype f16
+make llama-quantize
+./llama-quantize mindbot-f16.gguf mindbot-q4_k_m.gguf q4_k_m
+```
+
+## Model Family
+
+| Model | Type | Size |
+|-------|------|------|
+| [MindBot-Micro](https://huggingface.co/TheMindExpansionNetwork/MindBot-Micro) | LoRA adapter | 1.5B |
+| [MindBot-Standard](https://huggingface.co/TheMindExpansionNetwork/MindBot-Standard) | LoRA adapter | 4B |
+| **MindBot-Standard-Merged** | Full merged | 4B |
+
+## Part of TheMindExpansionNetwork 🌕