Full model card, rename files to Harmonic-Hermes-9B-*

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-9B-Harmonic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Qwen3.5-9B-Harmonic.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+Harmonic-Hermes-9B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Harmonic-Hermes-9B-BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,21 +1,124 @@
 ---
+language:
+- en
+license: apache-2.0
 tags:
 - gguf
+- qwen3.5
+- reasoning
+- chain-of-thought
+- self-correction
+- tool-calling
+- agent
+- hermes
 - llama.cpp
 - unsloth
-- vision-language-model
+- conversational
+base_model: DJLougen/Harmonic-Hermes-9B
 ---
 
-# Harmonic-Hermes-9B-GGUF : GGUF
+> ## ☕ Support This Work
+>
+> I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. It's a hobby that got out of hand. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.
+>
+> **[☕ ko-fi.com/djlougen](https://ko-fi.com/djlougen)**
 
-This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+# Harmonic-Hermes-9B-GGUF
 
-**Example usage**:
-- For text only LLMs:    `llama-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF --jinja`
-- For multimodal models: `llama-mtmd-cli -hf DJLougen/Harmonic-Hermes-9B-GGUF --jinja`
+GGUF quantizations of [Harmonic-Hermes-9B](https://huggingface.co/DJLougen/Harmonic-Hermes-9B) for local inference with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes.
 
-## Available Model files:
-- `Qwen3.5-9B-Harmonic.Q8_0.gguf`
-- `Qwen3.5-9B-Harmonic.BF16-mmproj.gguf`
-This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+Harmonic-Hermes-9B is the **Stage 2 agentic fine-tune** of [Harmonic-9B](https://huggingface.co/DJLougen/Harmonic-9B) — a dedicated tool-calling and agent model built on top of a strong reasoning backbone.
+
+Where Harmonic-9B teaches the model *how to think*, Harmonic-Hermes-9B teaches it *how to act* — structured tool use, multi-turn agent workflows, and function calling, all grounded in the reasoning depth from Stage 1.
+
+> **Stage 1** — [Harmonic-9B](https://huggingface.co/DJLougen/Harmonic-9B): Heavy reasoning fine-tune on privately generated, structurally validated data. Every row passes strict quality gates. The thinking backbone.
+>
+> **Stage 2** (this model): Agentic fine-tune on tool-calling and agent interaction data. Inherits Stage 1's reasoning depth and adds structured action capabilities.
+
+## Available Quantizations
+
+| File | Quant | Size | Use Case |
+|---|---|---|---|
+| `Harmonic-Hermes-9B-Q8_0.gguf` | Q8_0 | ~9.5 GB | Near-lossless, 16GB VRAM |
+
+More quantizations coming soon.
+
+### Vision (Multimodal)
+
+This model includes `Harmonic-Hermes-9B-BF16-mmproj.gguf` — the vision projector for multimodal inference. Use with llama.cpp's `--mmproj` flag for image understanding tasks.
+
+## What This Model Does
+
+- **Tool calling / function calling** — structured JSON tool use in the Hermes agent format
+- **Multi-turn agent workflows** — maintains coherent state across extended tool-use conversations
+- **Reasoning-grounded decisions** — inherits Harmonic-9B's self-correction, verification, and exploration before committing to actions
+
+## Training Approach
+
+Harmonic-Hermes-9B is a Stage 2 fine-tune of [Harmonic-9B](https://huggingface.co/DJLougen/Harmonic-9B), trained on curated agent interaction and tool-calling data.
+
+The key insight: most agent models are fine-tuned directly from base models or generic instruct tunes. They learn tool-call formatting but not *when* or *why* to use tools. By starting from a model that already reasons deeply (Stage 1), the agent behaviors are grounded in genuine multi-step thinking rather than pattern-matched tool invocations.
+
+## Usage
+
+### Ollama
+
+```
+ollama run DJLougen/Harmonic-Hermes-9B-GGUF
+```
+
+### llama.cpp
+
+```bash
+./llama-cli -m Harmonic-Hermes-9B-Q8_0.gguf -p "Use the available tools to..." -n 4096
+```
+
+### LM Studio
+
+Download any quantization and load in LM Studio. The model follows standard ChatML formatting.
+
+### Reasoning + Tool Use
+
+The model uses `<think>` blocks for reasoning before acting:
+
+```
+<think>
+The user wants to check the weather in Toronto. I have a get_weather tool available.
+Let me call it with the right parameters...
+</think>
+
+<tool_call>
+{"name": "get_weather", "arguments": {"location": "Toronto, Canada"}}
+</tool_call>
+```
+
+## Intended Use
+
+- Agentic workflows with tool calling and function execution
+- Multi-turn assistant interactions requiring structured reasoning
+- Local inference as an always-on agent backbone
+- Research into reasoning-grounded agent behavior
+
+## Limitations
+
+- 9B parameter model — not suitable for tasks requiring extensive world knowledge
+- Agent capabilities are shaped by the training data distribution
+- Benchmark evaluation is ongoing
+
+## Architecture
+
+- **Base**: [Harmonic-9B](https://huggingface.co/DJLougen/Harmonic-9B) (Stage 1 reasoning fine-tune of Qwen 3.5 9B)
+- **Parameters**: 9.65B
+- **Training**: LoRA fine-tuning, merged into base weights
+- **Precision**: BF16
+- **Context**: 8192 tokens
+
+## License
+
+Apache 2.0 — same as the base model. Fully commercial use permitted.
+
+## Links
+
+- Stage 2 full weights: [DJLougen/Harmonic-Hermes-9B](https://huggingface.co/DJLougen/Harmonic-Hermes-9B)
+- Stage 1 reasoning backbone: [DJLougen/Harmonic-9B](https://huggingface.co/DJLougen/Harmonic-9B)
+- Stage 1 GGUF quantizations: [DJLougen/Harmonic-9B-GGUF](https://huggingface.co/DJLougen/Harmonic-9B-GGUF)