Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,123 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: gguf
+pipeline_tag: text-generation
+model_name: Ornith-1.0-35B-TQ3_4S
+tags:
+- gguf
+- llama.cpp
+- qwen
+- qwen3.6
+- ornith
+- turboquant
+- tq3_4s
+base_model:
+- deepreinforce-ai/Ornith-1.0-35B
+model-index:
+- name: Ornith-1.0-35B-TQ3_4S
+  results: []
+---
+
+# Ornith-1.0-35B-TQ3_4S
+
+![Ornith-1.0-35B-TQ3_4S](thumbnail.png)
+
+`Ornith-1.0-35B-TQ3_4S` is a compact TurboQuant GGUF build of [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B).
+
+## Required Runtime
+
+This model uses the custom `TQ3_4S` tensor type and requires [turbo-tan/llama.cpp-tq3](https://github.com/turbo-tan/llama.cpp-tq3).
+
+> Stock `llama.cpp` builds without TurboQuant support cannot load this model.
+
+This is the standard 35B model, not an MTP release. Do not add draft-MTP speculative-decoding flags.
+
+## Files
+
+- [`Ornith-1.0-35B-TQ3_4S.gguf`](Ornith-1.0-35B-TQ3_4S.gguf) - main model, 13.30 GB (12.39 GiB)
+- [`thumbnail.png`](thumbnail.png) - model card banner
+- [`benchmark.png`](benchmark.png) - benchmark comparison card
+- [`benchmark_notes.md`](benchmark_notes.md) - compact benchmark provenance and comparison
+
+## Build the Required Runtime
+
+```bash
+git clone https://github.com/turbo-tan/llama.cpp-tq3
+cd llama.cpp-tq3
+
+cmake -S . -B build \
+  -DCMAKE_BUILD_TYPE=Release \
+  -DGGML_CUDA=ON \
+  -DGGML_CUDA_FA_ALL_QUANTS=OFF \
+  -DGGML_CUDA_GRAPHS=ON
+
+cmake --build build --target llama-server -j
+```
+
+For an RTX 3090, `-DCMAKE_CUDA_ARCHITECTURES=86` may be added explicitly. Use the architecture matching your GPU on other systems.
+
+## Recommended Runtime
+
+Validated on an NVIDIA GeForce RTX 3090 Founders Edition with 24 GiB VRAM:
+
+```bash
+./build/bin/llama-server \
+  -m Ornith-1.0-35B-TQ3_4S.gguf \
+  --alias Ornith-1.0-35B-TQ3_4S \
+  --host 127.0.0.1 --port 8080 \
+  -c 32768 -np 1 -ngl 99 -fa on \
+  -ctk q8_0 -ctv tq3_0 \
+  --reasoning off --jinja
+```
+
+Runtime notes:
+
+- `-fa on` enables flash attention at runtime.
+- The validated CUDA build uses `GGML_CUDA_FA_ALL_QUANTS=OFF`.
+- `-ngl 99` fully offloads the model on supported GPUs. Avoid partial offload when comparing the published speed.
+- Reduce context from `32768` if the available VRAM is lower than 24 GiB.
+
+## Quick Smoke Test
+
+```bash
+curl -s http://127.0.0.1:8080/v1/chat/completions \
+  -H 'Content-Type: application/json' \
+  -d '{"model":"Ornith-1.0-35B-TQ3_4S","messages":[{"role":"user","content":"Write ONLY the word ok."}],"max_tokens":16,"temperature":0.0}'
+```
+
+Expected assistant content:
+
+```text
+ok
+```
+
+## Benchmark Summary
+
+Local BenchLoop and Hard86 comparison on an RTX 3090 FE using the TurboTan runtime and the launch settings above:
+
+![Benchmark comparison](benchmark.png)
+
+| Metric | Result |
+|---|---:|
+| 35B field overall | 95.75 |
+| Hard86 | 81.4% |
+| EasyCode | 100.0% |
+| Toolcall | 88.3% |
+| Data extract | 86.5% |
+| Instruct follow | 65.5% |
+| Reason math | 73.3% |
+| Generation speed | 146.3 tok/s |
+| Size | 13.0 GB reported; 12.39 GiB file |
+
+The field score uses `0.85 * task_score + 0.15 * size_factor`, with size normalized to the smallest displayed 35B model. Hard86 is weighted at `2x`, EasyCode at `0.5x`, and the remaining benchmark categories at `1x`.
+
+
+## Validation Notes
+
+- Benchmark results are local measurements, not claims from the parent model repository.
+
+## License
+
+Use is subject to the [base model](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) license and the licenses of [turbo-tan/llama.cpp-tq3](https://github.com/turbo-tan/llama.cpp-tq3).