100 lines
5.3 KiB
Markdown
100 lines
5.3 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model: Delentia/delentia-slm-jitna-v0.4
|
|
tags:
|
|
- gguf
|
|
- llama-cpp
|
|
- text-generation
|
|
- tool-use
|
|
- delentia-os
|
|
- JITNA
|
|
- merged
|
|
---
|
|
|
|
# Delentia SLM — The Pre-Merged Executor v0.4 (slm-jitna-executor-v0.4)
|
|
|
|
[](https://github.com/delentia-labs/Delentia-OS)
|
|
[](https://github.com/delentia-labs/Delentia-OS)
|
|
|
|
> ⚙️ **Looking for the SDK & Source Code?**
|
|
> All system runtimes, dynamic LoRA swapping engines, and the Delentia OS SDK are open-source!
|
|
> 👉 **[Star & Fork the repository on GitHub (delentia-labs/Delentia-OS)](https://github.com/delentia-labs/Delentia-OS)**
|
|
|
|
---
|
|
|
|
This is the **Pre-Merged GGUF/Safetensors** version of **The Executor**, the tool-calling engine of **Delentia OS**. The Executor adapter has been merged directly into the base kernel weights for high performance local edge execution via Ollama or llama.cpp without needing external adapter loading.
|
|
|
|
## ⚡ Quick Start: Local Edge Execution via Ollama
|
|
|
|
To run this tool executor model locally in under 5 minutes:
|
|
|
|
1. Download the GGUF model binary: `delentia-slm-jitna-executor-v0.4-Q4_K_M.gguf`
|
|
2. Create a local `Modelfile` with the following configuration:
|
|
```dockerfile
|
|
FROM ./delentia-slm-jitna-executor-v0.4-Q4_K_M.gguf
|
|
|
|
TEMPLATE \"\"\"<|start_header_id|>system<|end_header_id|>
|
|
You are the Executor. Translate user intent into valid JSON/TOON format.
|
|
<|start_header_id|>user<|end_header_id|>
|
|
{{ .Prompt }}<|end_header_id|>
|
|
\"\"\"
|
|
```
|
|
3. Register and run the model via Ollama CLI:
|
|
```bash
|
|
ollama create delentia-executor -f Modelfile
|
|
ollama run delentia-executor
|
|
```
|
|
|
|
## ⚡ Quick Start: Python Transformers
|
|
|
|
Alternatively, run the merged weights directly using Python Hugging Face Transformers:
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "Delentia/delentia-slm-jitna-executor-v0.4"
|
|
|
|
# Load the merged weights directly
|
|
model = AutoModelForCausalLM.from_pretrained(model_name)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
```
|
|
|
|
## 🌐 Delentia OS Ecosystem Model Roster (v0.4.x)
|
|
Delentia OS is organized into two primary deployment styles: **Dynamic PEFT Adapters** (1+4 Pillars) for sub-ms switching in unified VRAM, and **Pre-Merged GGUF Models** for direct plug-and-play local execution in Ollama / llama.cpp.
|
|
|
|
| Component / Role | Deployment Type | Hugging Face Repository | Description | GGUF Support |
|
|
| :--- | :--- | :--- | :--- | :---: |
|
|
| **SLM Base Kernel** | Base Foundation | [Delentia/delentia-slm-jitna-v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-v0.4) | Core cognitive LLM (8B Parameters) | ✅ |
|
|
| **The Router** | PEFT LoRA Adapter | [Delentia/delentia-lora-router-v0.4](https://huggingface.co/Delentia/delentia-lora-router-v0.4) | Intention parser & node routing | ❌ (PEFT only) |
|
|
| **The Executor** | PEFT LoRA Adapter | [Delentia/delentia-lora-executor-v0.4](https://huggingface.co/Delentia/delentia-lora-executor-v0.4) | JSON tool payload generation | ✅ (Merged GGUF below) |
|
|
| **The Guardian** | PEFT LoRA Adapter | [Delentia/delentia-lora-guardian-v0.4](https://huggingface.co/Delentia/delentia-lora-guardian-v0.4) | Zero-trust constitutional safety | ✅ (Merged GGUF below) |
|
|
| **The Scribe** | PEFT LoRA Adapter | [Delentia/delentia-lora-scribe-v0.4](https://huggingface.co/Delentia/delentia-lora-scribe-v0.4) | Context compression/summarization | ✅ (Merged GGUF below) |
|
|
| **Pre-Merged Executor** | Pre-Merged GGUF | [Delentia/delentia-slm-jitna-executor-v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-executor-v0.4) | Complete tool executor (plug-and-play) | ✅ |
|
|
| **Pre-Merged Guardian** | Pre-Merged GGUF | [Delentia/delentia-slm-jitna-guardian-v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-guardian-v0.4) | Full safety guardrail model | ✅ |
|
|
| **Pre-Merged Scribe** | Pre-Merged GGUF | [Delentia/delentia-slm-jitna-scribe-v0.4](https://huggingface.co/Delentia/delentia-slm-jitna-scribe-v0.4) | Out-of-the-box context compressor | ✅ |
|
|
|
|
### 🔒 Empirical Audit Ledger
|
|
|
|
*ผลลัพธ์เฉพาะทางด้านล่าง ถูกสร้างและยืนยันผ่านกระบวนการนิติวิทยาศาสตร์ระบบ:*
|
|
|
|
|
|
|
|
- **Auditor Notebook:** `4_pillar_auditor_public.ipynb` ([Live Runtime](https://colab.research.google.com/drive/1fp3BOZNKPRJ82TTLHVLTWMcWuAdBLkif))
|
|
- **Run ID:** `c9e055c5-3919-4294-a4cd-67a3ce2a8d78`
|
|
- **Target Safetensors Hash:** `SHA256:5ea7e3a4504d618a36a4a10f93789bc83cb046f45df2f36250aa2865bf25f371`
|
|
- **Last Certified:** `2026-06-29T05:10:00Z`
|
|
|
|
| Gate Category | Specific Metric | Target | Empirical Result | Status |
|
|
",
|
|
|
|
"| :--- | :--- | :---: | :---: | :---: |
|
|
",
|
|
|
|
"| **Silicon Attestation** | PCIe VRAM Swap Latency | < 12.0 ms | **177.6014 ms** | Certified (Cloud) |
|
|
",
|
|
|
|
"| **Syntax Compiler** | JSON Parsing Syntax Error Rate | = 0.00% | **0.0000%** | Certified |
|
|
",
|
|
|
|
"| **Tool Calling** | Schema Strict Adherence Score | >= 95.00% | **98.00%** | Certified |
|