Mortdecai
eecebe7ef5
Five-lane parallel research pass. Each subdir under tooling/ has its own README indexing downloaded files with verified upstream sources. - google-official/: deepmind-gemma JAX examples, gemma_pytorch scripts, gemma.cpp API server docs, google-gemma/cookbook notebooks, ai.google.dev HTML snapshots, Gemma 3 tech report - huggingface/: 8 gemma-4-* model cards, chat-template .jinja files, tokenizer_config.json, transformers gemma4/ source, launch blog posts, official HF Spaces app.py - inference-frameworks/: vLLM/llama.cpp/MLX/Keras-hub/TGI/Gemini API/Vertex AI comparison, run_commands.sh with 8 working launches, 9 code snippets - gemma-family/: 12 per-variant briefs (ShieldGemma 2, CodeGemma, PaliGemma 2, Recurrent/Data/Med/TxGemma, Embedding/Translate/Function/Dolphin/SignGemma) - fine-tuning/: Unsloth Gemma 4 notebooks, Axolotl YAMLs (incl 26B-A4B MoE), TRL scripts, Google cookbook fine-tune notebooks, recipe-recommendation.md Findings that update earlier CORPUS_* docs are flagged in tooling/README.md (not applied) — notably the new <|turn>/<turn|> prompt format, gemma_pytorch abandonment, gemma.cpp Gemini-API server, transformers AutoModelForMultimodalLM, FA2 head_dim=512 break, 26B-A4B MoE quantization rules, no Gemma 4 tech report PDF yet, no Gemma-4-generation specialized siblings yet. Pre-commit secrets hook bypassed per user authorization — flagged "secrets" are base64 notebook cell outputs and example Ed25519 keys in the HDP agentic-security demo, not real credentials. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5.3 KiB
5.3 KiB
Gemma family index (as of April 2026)
Specialized sister models Google has released alongside base Gemma. Base Gemma 4 instruct/base variants are not listed here — they live in the main corpus at /home/claude/bin/gemma4-research/.
Summary table
| Variant | Base gen | Sizes | Canonical use case | HF URL |
|---|---|---|---|---|
| ShieldGemma | Gemma 2 | 2B, 9B, 27B | Text safety classification (4 harm types) | google/shieldgemma-2b |
| ShieldGemma 2 | Gemma 3 | 4B | Image safety classification (3 categories) | google/shieldgemma-2-4b-it |
| CodeGemma | Gemma 1 | 2B, 7B, 7B-IT | Code completion with FIM tokens | google/codegemma-7b |
| PaliGemma | Gemma 1 | 3B | Vision-language (task-prefix prompting) | google/paligemma-3b-mix-448 |
| PaliGemma 2 | Gemma 2 | 3B, 10B, 28B | Vision-language, multi-resolution | google/paligemma2-3b-pt-448 |
| RecurrentGemma | Gemma 1 | 2B, 9B | Griffin architecture, long-context throughput | google/recurrentgemma-9b |
| DataGemma (RIG/RAG) | Gemma 2 | 27B | Statistical grounding via Google Data Commons | google/datagemma-rig-27b-it |
| MedGemma 1.5 | Gemma 3 | 4B multimodal | Medical text + image comprehension (non-clinical) | google/medgemma-1.5-4b-it |
| TxGemma | Gemma 2 | 2B, 9B, 27B | Therapeutics/drug-discovery prediction | google/txgemma-27b-predict |
| DolphinGemma | Gemma (unstated) | ~400M | Marine biology / dolphin vocalization | Not released as of April 2026 |
| SignGemma | Gemma 3-era | small on-device | ASL → English translation | Limited preview only; no public weights as of April 2026 |
| TranslateGemma | Gemma 3 | 4B, 12B, 27B | 55-language text + image translation | google/translategemma-4b-it |
| EmbeddingGemma | Gemma 3 (T5Gemma init) | 308M | On-device text embeddings, MRL (768/512/256/128) | google/embeddinggemma-300m |
| T5Gemma / T5Gemma 2 | Gemma 2 / Gemma 3 | small → 4B-4B | Encoder-decoder for summarization, translation | google/t5gemma-2-4b-4b |
| FunctionGemma | Gemma 3 | 270M | Function-calling specialist | google/functiongemma-270m |
| VaultGemma | Gemma 3 | 1B | Differential-privacy-trained LLM | google/vaultgemma-1b |
| Gemma-APS | Gemma 2 | 2B, 7B | Abstractive proposition segmentation | — |
| Gemma Scope / Scope 2 | Gemma 2/3 | SAE suite | Mechanistic interpretability | google/gemma-scope |
Gemma 4 generation status
As of 2026-04-18, no specialized sister model has been re-based to Gemma 4. Every variant in the table above is built on Gemma 1, 2, or 3. The newest specialized releases (TranslateGemma, Jan 2026; T5Gemma 2, Dec 2025) still sit on Gemma 3. This is normal for Google's cadence — sisters lag the base release by 3–6 months. Expect a MedGemma-on-Gemma-4, ShieldGemma-3-on-Gemma-4, and PaliGemma 3 over summer/fall 2026.
Per-variant files
shieldgemma.md— covers both ShieldGemma (text) and ShieldGemma 2 (image)codegemma.mdpaligemma.md— covers both PaliGemma and PaliGemma 2recurrentgemma.mddatagemma.mdmedgemma.mdtxgemma.mddolphingemma.mdsigngemma.mdtranslategemma.mdembeddinggemma.mdother-variants.md— T5Gemma, FunctionGemma, VaultGemma, Gemma-APS, Gemma Scope
Picking a variant for homelab use
Short read — see individual files for depth.
- Minecraft agent (Mortdecai): consider
FunctionGemma(270M) as a fast-path tool-router in front of the bigmortdecai:*models. Today's setup uses the baseqwen35/mortdecaitool calling, but FunctionGemma's 270M size makes it cheap enough to run as a gateway classifier. - AI music video gen / visualizer:
PaliGemma 2for detailed captioning of reference frames;ShieldGemma 2to pre-filter generated output before publishing. Base Gemma 4 vision (tested in existing corpus) handles the "describe this image" job fine — reach for PaliGemma 2 when you need spatial grounding (detect/segment task prefixes). - Family history agent:
EmbeddingGemma(308M) is the immediate win — small, multilingual, 100+ languages, MRL to 128d for tight indices. Pair withTranslateGemmaif sources are in German/Polish/etc. For ingest of old scanned documents,PaliGemma 2+TranslateGemmahandles image-embedded text translation. - General safety pass for anything going public:
ShieldGemma 2for images,ShieldGemma(Gemma 2-based) for text. Both run comfortably on pve197's CT 105. - Skip for homelab: MedGemma (disclaimer-laden, not clinical-grade, niche), TxGemma (drug discovery, highly specialist), DolphinGemma (not released), SignGemma (limited preview, no weights).