RingoLLM v4.2 - Q5_K_M GGUF, model card, chat template

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+RingoLLM-v42-qwen35-27B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+base_model:
+  - unsloth/Qwen3.6-27B
+  - Qwen/Qwen3.6-27B
+base_model_relation: finetune
+pipeline_tag: text-generation
+library_name: gguf
+language:
+  - en
+tags:
+  - gguf
+  - llama.cpp
+  - windows
+  - powershell
+  - intune
+  - dsc
+  - endpoint-management
+---
+
+# ringollm-v42
+
+A LoRA fine-tune of [unsloth/Qwen3.6-27B](https://huggingface.co/unsloth/Qwen3.6-27B) specialised for
+**Windows endpoint management**: DSC v3, DSC Legacy, PowerShell 7, Intune deployment
+(Settings Catalog, OMA-URI, IME, Win32 packaging, Proactive Remediations) and
+endpoint-side Entra ID diagnostics.
+
+Quantized to **Q5_K_M** for llama.cpp.
+
+## Why this exists
+
+Earlier releases emitted `securityContext: Elevated` in DSC v3 documents. That is
+**schema-invalid**. `dsc-lib`'s `SecurityContextKind` is declared
+`#[serde(rename_all = "camelCase")]`, so only `current`, `elevated` and `restricted`
+deserialize — the PascalCase form fails outright. Microsoft Learn's `ValidValues` table
+lists the capitalised spellings and is wrong. This release emits the lowercase enum.
+
+## Measured results
+
+| metric | ringollm-v4 | ringollm-v42 |
+|---|---|---|
+| rubric checks passed | 110/129 (85.3%) | 112/129 (86.8%) |
+| questions passed | 14/25 (56.0%) | 17/25 (68.0%) |
+| securityContext valid / invalid | 0 / 6 | 8 / 0 |
+| median tok/s | 11.26 | 11.29 |
+
+## Usage
+
+llama.cpp:
+
+```bash
+llama-server -m RingoLLM-v42-qwen35-27B-Q5_K_M.gguf \
+  --jinja --chat-template-file ringollm-v42.jinja \
+  -ngl 999 -fa on -np 1 \
+  -c 65536 --cache-type-k q8_0 --cache-type-v q8_0 --kv-unified \
+  --temp 0.3 --top-p 0.9 --repeat-penalty 1.15 --repeat-last-n 256
+```
+
+Ollama:
+
+```bash
+ollama create ringollm-v42 -f Modelfile
+ollama run ringollm-v42
+```
+
+### Serving parameters, and why
+
+| flag | value | why it matters |
+|---|---|---|
+| `--chat-template-file` | `ringollm-v42.jinja` | **Required.** Ships in this repo. It injects the default system prompt that defines scope and the refusal format. Without it the model loses all refusal behaviour. |
+| `--kv-unified` | on | **Stability, not tuning.** On RADV / AMD Strix Halo this architecture hard-hangs the GPU on prompts past ~20k tokens without it — `vk::Queue::submit: ErrorDeviceLost`, an `amdgpu ring timeout`, and a reset that takes down unrelated processes. Upstream issue closed as not-planned, so there is no fix to wait for. Harmless on other backends; leave it on. |
+| `--cache-type-k/v` | `q8_0` | Pairs with `--kv-unified` to make long contexts affordable and stable. |
+| `-c` | 65536 | Observed real-world high-water is ~26k tokens. |
+| `-np` | 1 | Recurrent state is allocated **per slot**; more slots divide the usable context. |
+| `-fa` | on | Flash attention. |
+| `--temp` / `--top-p` | 0.3 / 0.9 | What the model was evaluated with. |
+| `--repeat-penalty` / `--repeat-last-n` | 1.15 / 256 | As evaluated. |
+
+## Prompting
+
+The chat template injects a default system prompt when the caller supplies none. It
+defines the scope and the refusal format for out-of-scope questions, so **omit the
+system message** unless you intend to replace that behaviour entirely.
+
+## Training data
+
+All training pairs are derived from Microsoft documentation, the DSC resource registry and the published JSON schemas via deterministic builders. **No LLM-generated text is present in the training data.**
+
+## Limitations
+
+- Scoped to Windows endpoint management. It is instructed to refuse elsewhere, and will.
+- Served with reasoning suppressed; the template pre-closes the `<think>` block.
+- Quantized to Q5_K_M; expect small deviations from the full-precision merge.

RingoLLM-v42-qwen35-27B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843d3b1647fe44afb994aa18ea2617c1b5d294d4a44d4002354fdd5c5c21c248
+size 19231098048

ringollm-v42.jinja

@@ -0,0 +1,13 @@
+{%- if messages and messages[0].role == 'system' -%}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' -}}
+{%- set loop_messages = messages[1:] -%}
+{%- else -%}
+{{- '<|im_start|>system\n' + "You are RingoLLM v4.2, a specialized AI assistant for Windows endpoint management. You focus on DSC v3, DSC Legacy, PowerShell 7, Intune endpoint deployment (Settings Catalog, OMA-URI, IME, Win32 packaging, Proactive Remediations), and endpoint-side Entra ID diagnostics.\n\nWhen asked about topics outside this scope (Cisco/network appliances, Linux administration, KQL/Sentinel, WDAC/App Control, Microsoft Graph SDK administration, macOS, etc.), respond with a brief refusal in this format:\n\n\"I don't have reliable information on [topic]. This is outside my focus on Windows endpoint management. For authoritative guidance, see [vendor's official documentation].\"\n\nDo not invent cmdlets, parameters, configuration syntax, or commands for tools you don't have specific training on. If you're uncertain about a specific cmdlet or syntax, say so explicitly." + '<|im_end|>\n' -}}
+{%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+{{- '<|im_start|>assistant\n<think>\n\n</think>\n\n' -}}
+{%- endif -%}