Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+aac-board-generator-770m-ptbr-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+aac-board-generator-770m-ptbr-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+aac-board-generator-770m-ptbr-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+aac-board-generator-770m-ptbr-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+aac-board-generator-770m-ptbr-f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+language:
+- pt
+license: gemma
+library_name: gguf
+pipeline_tag: text-generation
+base_model: tardellirs/aac-board-generator-770m-ptbr
+tags:
+- gguf
+- llama-cpp
+- text-generation
+- gemma3
+- aac
+- augmentative-alternative-communication
+- arasaac
+- board-generation
+- brazilian-portuguese
+- cpu
+---
+
+# AAC Board Generator 770M (pt-BR) — GGUF
+
+![Runs on](https://img.shields.io/badge/runs%20on-CPU-success)
+[![Model](https://img.shields.io/badge/model-card-blue)](https://huggingface.co/tardellirs/aac-board-generator-770m-ptbr)
+[![License](https://img.shields.io/badge/license-Gemma-lightgrey)](https://ai.google.dev/gemma/terms)
+[![Used in Papuguinho](https://img.shields.io/badge/used%20in-Papuguinho-ff69b4)](https://www.papuguinho.com)
+
+`llama.cpp` **GGUF builds** of [**aac-board-generator-770m-ptbr**](https://huggingface.co/tardellirs/aac-board-generator-770m-ptbr)
+— a 771.6M Brazilian-Portuguese **multi-function AAC** model that drafts **pictogram-board** word lists *and* follows
+in-assistant board-editing instructions (add / remove / generate N), on **CPU**. See the
+[**model card**](https://huggingface.co/tardellirs/aac-board-generator-770m-ptbr) for what it does, training, and
+evaluation.
+
+## Files
+
+| File | Quant | Size | Notes |
+|---|---|---|---|
+| `aac-board-generator-770m-ptbr-Q4_K_M.gguf` | Q4_K_M | 561 MB | smallest; slight quality drop |
+| `aac-board-generator-770m-ptbr-Q5_K_M.gguf` | Q5_K_M | 606 MB | good size/quality balance |
+| `aac-board-generator-770m-ptbr-Q6_K.gguf`   | Q6_K   | 766 MB | near-lossless |
+| `aac-board-generator-770m-ptbr-Q8_0.gguf`   | Q8_0   | 824 MB | **recommended** — safe near-lossless |
+| `aac-board-generator-770m-ptbr-f16.gguf`    | f16    | 1.55 GB | full precision reference |
+
+At **Q8_0** the model needs on the order of **~0.9–1.1 GB RAM** to serve (weights + a small context) and produces a
+~12-item board in **about 4 s on 4 CPU threads**.
+
+## Usage
+
+```bash
+llama-server -m aac-board-generator-770m-ptbr-Q8_0.gguf -t 4 -c 2048 --host 127.0.0.1 --port 8080
+```
+
+Gemma has no system role — put the instruction in the user turn and call `/completion`:
+
+```python
+import requests
+INSTR = ("Você monta pranchas de CAA (pictogramas, pt-BR). Para o PEDIDO, liste ~12 itens concretos e relevantes, "
+         "um por linha, no formato palavra|tipo|sinônimos (tipo: v/s/a/e/l/p). Só a lista.")
+pedido = "monta uma prancha de brincar no parquinho"
+prompt = f"<start_of_turn>user\n{INSTR}\n\nPEDIDO: {pedido}<end_of_turn>\n<start_of_turn>model\n"
+print(requests.post("http://127.0.0.1:8080/completion",
+                    json={"prompt": prompt, "temperature": 0, "n_predict": 320}).json()["content"])
+```
+
+Generation is **greedy / deterministic** (`temperature 0`). Output is one item per line, `word|type|synonyms`.
+
+## Notes on the build (why these GGUFs are faithful)
+
+This model is a **vocabulary-trimmed** Gemma 3 (262k → 64k tokens). A reconstructed SentencePiece tokenizer is *not*
+bit-exact for a trimmed vocabulary and would silently degrade greedy generation. These GGUFs instead use the
+**BPE `tokenizer.json`** path, which tokenizes **identically** to the original — so the quantized model reproduces the
+untrimmed parent's outputs. Verified: identical token counts and identical boards vs. the fp16 reference.
+
+## License & attribution
+
+Released under the **[Gemma license](https://ai.google.dev/gemma/terms)** (inherited from Gemma 3). Built for the
+**ARASAAC** ecosystem (CC BY-NC-SA content). See the
+[model card](https://huggingface.co/tardellirs/aac-board-generator-770m-ptbr) for full terms.
+
+Developed for and used in **Papuguinho** — [www.papuguinho.com](https://www.papuguinho.com).

aac-board-generator-770m-ptbr-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12af32ebb0193e434d6509dc530f7e066bad8d521fd53b9689108641101fc044
+size 560686304

aac-board-generator-770m-ptbr-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5e2902588bbce59bfa1e64435b419c24ab384bde44da67b7044d42d742a562
+size 605973728

aac-board-generator-770m-ptbr-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db4f8f5c3786e110f5ec9d2fb121ff94e6b28c6ce32b057ec39a82798ede73a
+size 766366688

aac-board-generator-770m-ptbr-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a245b424d904a9a1e50e20aec3ec90e49a40f78f9898b0c55bc4ca251b28968
+size 823934432

aac-board-generator-770m-ptbr-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79da518283053b1dc9b0a3589fd092b7ecba60c9a0c622c46963142973447838
+size 1547209344