commit ad9050d6ecb876a84cfbe4da9d57d6959577d4af Author: ModelHub XC Date: Tue Sep 1 14:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: occ-ai/OCC-RAG-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7dde7b4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 +OCC-RAG-0.6B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-BF16.gguf filter=lfs diff=lfs merge=lfs -text +OCC-RAG-0.6B-F16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OCC-RAG-0.6B-BF16.gguf b/OCC-RAG-0.6B-BF16.gguf new file mode 100644 index 0000000..21404b0 --- /dev/null +++ b/OCC-RAG-0.6B-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257f1632e22a2f5feec0d2e17b7a72868057ad1d82c983a0148b4cb55d0a57c5 +size 1198179456 diff --git a/OCC-RAG-0.6B-F16.gguf b/OCC-RAG-0.6B-F16.gguf new file mode 100644 index 0000000..de99216 --- /dev/null +++ b/OCC-RAG-0.6B-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bacaa7a253e37337166e60bb32656e60b1e9c31e9df78534d250f286b1cb423f +size 1198179456 diff --git a/OCC-RAG-0.6B-Q4_0.gguf b/OCC-RAG-0.6B-Q4_0.gguf new file mode 100644 index 0000000..87426e1 --- /dev/null +++ b/OCC-RAG-0.6B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbd0d9ad35c1fddf88eb3822f90ea5c76189d98c2d4ef3998bb357ec4037886 +size 381563008 diff --git a/OCC-RAG-0.6B-Q4_K_M.gguf b/OCC-RAG-0.6B-Q4_K_M.gguf new file mode 100644 index 0000000..1b4b0b2 --- /dev/null +++ b/OCC-RAG-0.6B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0bf248d0cdd60ea37c0fa092134acea35ee4bca0ee11ee031b91bf04281d17 +size 396701824 diff --git a/OCC-RAG-0.6B-Q5_K_M.gguf b/OCC-RAG-0.6B-Q5_K_M.gguf new file mode 100644 index 0000000..4fc5365 --- /dev/null +++ b/OCC-RAG-0.6B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e04b5783659924736721cb665f73698877064e89f50df281a5855d45f824f6 +size 444412032 diff --git a/OCC-RAG-0.6B-Q6_K.gguf b/OCC-RAG-0.6B-Q6_K.gguf new file mode 100644 index 0000000..6653c1c --- /dev/null +++ b/OCC-RAG-0.6B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2850f0908b62337163f02440b72cdf744b9c2c9847a4e844b2bbf3036bc792a1 +size 495104128 diff --git a/OCC-RAG-0.6B-Q8_0.gguf b/OCC-RAG-0.6B-Q8_0.gguf new file mode 100644 index 0000000..dcdab6e --- /dev/null +++ b/OCC-RAG-0.6B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be84ff20644203600c09d217eff3b8b491513fe79e1e2ee594bbc7f06574b5c7 +size 639444096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16960f9 --- /dev/null +++ b/README.md @@ -0,0 +1,120 @@ +--- +license: mit +language: +- en +- ru +library_name: gguf +pipeline_tag: text-generation +base_model: +- occ-ai/OCC-RAG-0.6B +tags: +- rag +- faithful-qa +- occ +- gguf +- llama.cpp +- quantized +--- + +# OCC-RAG-0.6B-GGUF + +

+ OCC-RAG +

+ +

+  GitHub  |  + Technical Report  |  + Cloud  |  + Base model +

+ +**GGUF quantizations of [`occ-ai/OCC-RAG-0.6B`](https://huggingface.co/occ-ai/OCC-RAG-0.6B)** +for native inference with [llama.cpp](https://github.com/ggml-org/llama.cpp), +[Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), and other +GGUF-compatible runtimes. + +OCC-RAG-0.6B is a 0.6B-parameter small language model specialized for **faithful, +context-grounded question answering**: given a question and a set of sources, it +produces a structured reasoning trace with explicit source citations, decides whether +the context supports an answer, and either answers from the context or abstains. See the +[base model card](https://huggingface.co/occ-ai/OCC-RAG-0.6B) for training details and +benchmarks. + +## Files + +The underlying architecture is Qwen3 (0.6B). The chat template is embedded in the GGUF, +so `llama.cpp`/Ollama apply it automatically. + +| File | Quant | Size | Notes | +|---|---|---|---| +| `OCC-RAG-0.6B-Q4_0.gguf` | Q4_0 | 0.38 GB | 4-bit, legacy — smallest | +| `OCC-RAG-0.6B-Q4_K_M.gguf` | Q4_K_M | 0.40 GB | 4-bit K-quant — **recommended balance** | +| `OCC-RAG-0.6B-Q5_K_M.gguf` | Q5_K_M | 0.44 GB | 5-bit K-quant | +| `OCC-RAG-0.6B-Q6_K.gguf` | Q6_K | 0.50 GB | 6-bit K-quant | +| `OCC-RAG-0.6B-Q8_0.gguf` | Q8_0 | 0.64 GB | 8-bit — near-lossless | +| `OCC-RAG-0.6B-F16.gguf` | F16 | 1.20 GB | 16-bit float (full precision) | +| `OCC-RAG-0.6B-BF16.gguf` | BF16 | 1.20 GB | 16-bit bfloat (lossless base) | + +For most uses pick **Q4_K_M** (smallest good quality) or **Q8_0** (highest quality at +under a GB). All quants are derived from the BF16 base. + +## Usage — llama.cpp + +```bash +# Run directly from the Hub (downloads the chosen quant) +llama-cli -hf occ-ai/OCC-RAG-0.6B-GGUF:Q4_K_M -p "Hello" -no-cnv + +# Or download a file and run it +llama-cli -m OCC-RAG-0.6B-Q4_K_M.gguf -p "Hello" -no-cnv +# (newer llama.cpp: use `llama-completion` for non-interactive runs) +``` + +## Usage — Ollama + +```bash +ollama run hf.co/occ-ai/OCC-RAG-0.6B-GGUF:Q4_K_M +``` + +## Input / output format + +OCC-RAG uses a **structured RAG prompt with special tokens**: the question is wrapped in +`<|query_start|> … <|query_end|>` and each source in +`<|source_start|><|source_id|>N … <|source_end|>`. The response has five sections — +**query analysis → source analysis → reasoning → status (`ANSWERABLE` / `UNANSWERABLE`) +→ answer** — and the final answer is in `<|answer_start|> … <|answer_end|>`. + +The embedded chat template (apply with llama.cpp's `--jinja`) builds the query/source +tokens for you when sources are supplied as documents; alternatively assemble the tokens +manually. See the [base model card](https://huggingface.co/occ-ai/OCC-RAG-0.6B) for the +full format and a runnable example. + +> We recommend **greedy decoding** (`--temp 0`), the training/evaluation default. + +## Limitations + +- **Context-grounded only.** Trained to answer from the supplied sources and to ignore + parametric knowledge — not a general-purpose chat or knowledge model. +- **Reasoning depth.** Training/evaluation are capped at three-hop reasoning; longer + chains are out of distribution. +- **Quantization.** Lower-bit quants (Q4) trade some quality for size; prefer Q6_K/Q8_0 + when accuracy matters most. + +## License + +Released under the [MIT License](https://huggingface.co/occ-ai/OCC-RAG-0.6B), inherited +from the base model. + +## Citation + +```bibtex +@misc{savkin2026occragoptimalcognitivecore, + title = {OCC-RAG: Optimal Cognitive Core for Faithful Question Answering}, + author = {Maksim Savkin and Mikhail Goncharov and Alexander Gambashidze and Alla Chepurova and Dmitrii Tarasov and Nikita Andriianov and Daria Pugacheva and Vasily Konovalov and Andrey Galichin and Ivan Oseledets}, + year = {2026}, + eprint = {2606.00683}, + archivePrefix = {arXiv}, + primaryClass = {cs.CL}, + url = {https://arxiv.org/abs/2606.00683} +} +``` diff --git a/figures/github-mark.png b/figures/github-mark.png new file mode 100644 index 0000000..e815117 Binary files /dev/null and b/figures/github-mark.png differ diff --git a/figures/occ.png b/figures/occ.png new file mode 100644 index 0000000..6834a22 Binary files /dev/null and b/figures/occ.png differ