Open-Weight Models Under Gemma Terms of Use

Model · Sentence similarity

embeddinggemma-300m

Google

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages. The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.…

Model · Text generation

gemma-3-1b-it

Google

[Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous…

Model · Image and text to text

gemma-3-4b-it

Google

[Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous…

Model · Text generation

gemma-2-9b-it

Google

[Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma] Summary description and brief definition of inputs and outputs. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them…

Gemma4-12B (QAT) uncensored by HauhauCS. 0/465 Refusals No changes to datasets or capabilities — fully functional, 100% of what the original authors intended, just without the refusals. Built from the official QAT weights, so the 4-bit quant stays close to full-precision quality. The Balanced variant (recommended — 99%+ of users will be happy here) uses optimized full uncensoring tuned especially for agentic coding, reasoning, creative writing and reliability-critical tasks. It reasons before answering and stays dependable and on-instruction. An Aggressive variant, for cases where Balanced still deflects too much, after current testing is not required. Ships with an MTP…

Model · Image and text to text

vllm-translategemma-4b-it

Infomaniak Network SA

This is a modified version of google/translategemma-4b-it optimized for deployment with vLLM. The original TranslateGemma model requires a structured payload with dedicated sourcelangcode and targetlangcode fields: However, vLLM does not support these custom content parameters. To maintain compatibility, the chat template has been modified to encode language codes directly in the message content using a delimiter-based format: Format: >>{sourcelang} >>{targetlang} >>{texttotranslate} If you need to provide a custom prompt input The original model uses the new Transformers RoPE configuration format with separate attention type settings: This has been simplified for vLLM compatibility: The…

Model · Robotics

pi0_base

LeRobot

π₀ is a Vision-Language-Action (VLA) foundation model from Physical Intelligence that jointly reasons over vision, language, and actions to control robots, serving as the base architecture that later enabled π₀.₅’s open-world generalization. Original paper: π0: A Vision-Language-Action Flow Model for General Robot Controlion For full installation details (including optional video dependencies such as ffmpeg for torchcodec), see the official documentation: https://huggingface.co/docs/lerobot/installation If you’re training / fine-tuning, you typically call forward(...) to get a loss and then: - -policy.chunksize=... - -policy.nactionsteps=... - -policy.maxactiontokens=...…

Model · Text generation

vllm-translategemma-12b-it

Bae chang hyun

This is a modified version of google/translategemma-12b-it optimized for deployment with vLLM. No retraining was performed. Only configuration files and the chat template were modified. Model weights are identical to the original. As of 2025-01-29, vLLM does not natively support TranslateGemma's custom structured input format. See vllm-project/vllm#32446 for the upstream tracking issue. Until that is merged, this repo provides a workaround by modifying configuration files to make TranslateGemma compatible with vLLM's standard chat API. This conversion is based entirely on the work done by Infomaniak-AI/vllm-translategemma-4b-it. The same conversion approach was applied to the 12B model.…

Model · Robotics

pi05_libero_finetuned_v044

LeRobot

π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Checkpoint trained and evaluated on LIBERO tasks Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full…

Model · Robotics

pi05_base

LeRobot

π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…

Model · Robotics

pi05_libero_base

LeRobot

π₀.₅ is a Vision-Language-Action (VLA) model with open-world generalization from Physical Intelligence, co-trained on robot demonstrations and large-scale multimodal data to execute long-horizon tasks in unseen real-world environments. Note: This model currently supports only the flow-matching action head for π₀.₅ training and inference. Other components from the original work (e.g., subtask prediction, action tokenization, or RL) were not released upstream and are not included here, though the LeRobot team is actively working to support them. Original paper: π0.5: A Vision-Language-Action Model with Open-World Generalization For full installation details (including optional video…

Model · Text generation

Gemma-3-270m-Opus-Distil

Convergent Intelligence

This model is a fine-tuned derivative of google/gemma-3-270m, adapted using the Convergent Intelligence sparse fine-tuning setup originally tested on Liquid Foundation Models. The checkpoint was trained on reasoning-style English examples from angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k using a targeted adaptation strategy and the custom CIxOpt optimizer framework. The goal of this model is to test whether a compact Gemma 3 270M backbone can be shaped toward reasoning-style text generation through selective parameter participation rather than broad full-model modification. This is an experimental research checkpoint intended for evaluation, local testing, optimizer research, and…

Most language models today act as polite chatbots: they offer conversational summaries, generic advice, and surface-level bullet points. But when the stakes are existential — when critical production services fail, corporate partnerships fracture, infrastructure is compromised, or you are facing high-consequence decisions under severe uncertainty — you don't need a conversational chatbot. You need a dedicated Directorate of Intelligence on your team. What if you could run an autonomous operational intelligence analyst directly on your local workstation — 100% private, offline, and air-gapped? That is the genesis of Sovereign Gotham / Sovereign Anthology. Rather than feeding an AI thousands…

Model · Text ranking

GemmaDecision-270M

Rajan Shukla

A fully tuned Gemma-270M candidate ranker: it scores each supplied choice together with the request, using a scalar decision head. Intended research tasks are banking-support topic selection and three-way evidence relations. It does not generate answers. The complete modified encoder and head are included. On the private fresh-prompt test, accuracy is 96.50% for four-way banking topics and 78.00% for three-way NLI, with an equal-family mean of 87.25%. Both frozen task targets were met on this private test. See RESULTS.md for both baselines, paired uncertainty, coverage, synthetic challenge results and failures. Package 0.2.0 uses ONNX Runtime on CPU by default. The standard install requires…

Gemma 4 E4B-IT uncensored by HauhauCS. 0/465 Refusals\ No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals. These are meant to be the best lossless uncensored models out there. Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated. For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available. All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights. KP ("Perfect")…

Model · Image and text to text

gemma-3-27b-it-int4-awq

Thien Tran

This is the QAT INT4 Flax checkpoint (from Kaggle) converted to HF+AWQ format for ease of use. AWQ was NOT used for quantization. You can find the conversion script convertflax.py in this model repo. NOTE: this is NOT the same as the official QAT INT4 GGUFs released here https://huggingface.co/collections/google/gemma-3-qat-67ee61ccacbf2be4195c265b Below is the original Model card from https://huggingface.co/google/gemma-3-27b-it [Gemma 3 Technical Report][g3-tech-report] [Responsible Generative AI Toolkit][rai-toolkit] [Gemma on Kaggle][kaggle-gemma] [Gemma on Vertex Model Garden][vertex-mg-gemma3] Summary description and brief definition of inputs and outputs. Gemma is a family of…

Model · Image and text to text

gemma-3-27b-it-GPTQ-4b-128g

IST Austria Distributed Algorithms and Systems Lab

This model was obtained by quantizing the weights of gemma-3-27b-it to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within languagemodel transformers blocks are quantized. Vision model and multimodal projection are kept in original precision. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization. Model checkpoint is saved in compressedtensors format. This model was evaluated on the OpenLLM v1 benchmarks. Model outputs were generated with the vLLM engine. The…

Model · Sentence similarity

embeddinggemma-300m

LiteRT Community (FKA TFLite)

This model card provides a few variants of the EmbeddingGemma model that are ready for deployment on Android and iOS using LiteRT, or on Android via the Google AI Edge RAG Library. Try out the demo example on GitHub. Try out the EmbeddingGemma model in the in the Google AI Edge RAG Library. You can find the SDK on GitHub or follow our Android guide to install directly from Maven. We have also published a sample app. Use the sentencepiece model as the tokenizer for the EmbeddingGemma model. Note that all benchmark stats are from a Samsung S25 Ultra. Mixed Precision refers to per-channel quantization with int4 for embeddings, feedforward, and projection layers, and int8 for attention…

Quantized Gemma 4 26B WebGPU.litertlm bundles for LiteRT-LM Web, with support for: - Text Decoder + Neural Multi-Token Prediction (MTP) speculative decoding (gpuartisan) - Multimodal Vision (visionencoder + visionadapter + endofvision, supporting variable token budgets [70, 140, 280, 560, 1120]) - Multimodal Audio (audioencoderhw Conformer + audioadapter + endofaudio) - gemma-4-26B-it-web-mtp.litertlm - gemma-4-26B-it-web-mtp-vision.litertlm - gemma-4-26B-it-web-mtp-audio.litertlm - gemma-4-26B-it-web-mtp-vision-audio.litertlm

galakenya/JapanRailwaySimLLM は、日本の鉄道技術仕様、運行管理規則、安全基準に特化した高度専門知識LLMモデルです。PDFドキュメントをベースにした多言語RAG対応設計となっています。 JapanRailwaySimLLM は、Googleの Gemma-2-9b-it をベースに、日本の鉄道ドメインに特化してQLoRAファインチューニングされたアダプターモデル、および高精度な量子化モデル（GGUF版）です。高精度なRAG (Retrieval-Augmented Generation) と連携させるための設定ファイル群およびPDFドキュメントが同封されています。 本モデルは、日本の鉄道における保安システム、車両設計、ダイヤ管理などの膨大な技術ドキュメント（「日本の鉄道技術図鑑集.pdf」および「Japanese Railway Technology Encyclopedia.pdf」など）および精密な解説データ（JSONL形式）をベースにファインチューニングされています。 JapanRailwayLLM.GGUF は llama.cpp や koboldcpp などの主要なGGUF推論エンジンでそのまま動作します。 JapanRailwaySimLLM is a 9B parameter specialized railway domain model, fine-tuned from Gemma-2-9b-it via QLoRA. It supports advanced multi-lingual RAG search backed by…

basemodel: google/gemma-2-9b-it - railway - japan - railroad - qlora - lora - gguf - rag - multilingual JapanRailwayLLM is a specialized railway large language model project focused on Japanese railway technology, operations, signaling systems, rolling stock engineering, infrastructure, transportation history, and railway regulations. JapanRailwayLLM は、日本の鉄道技術・運行管理・保安装置・信号システム・車両工学・鉄道インフラ・鉄道史・運賃制度・鉄道法規を対象とした専門AIモデルです。 google/gemma-2-9b-it https://galakenya.blogspot.com/ JapanRailwayLLM is a railway-specialized language model focusing on Japanese railway technology, operations, rolling stock engineering, infrastructure, signaling systems, railway regulations, and railway history.…

Model

functiongemma-langcalc-en.zh

Jeffrey Dick

A fine-tuned model based on google/functiongemma-270m-it.

Quantized Gemma 4 12B WebGPU.litertlm bundles for LiteRT-LM Web, with support for: - Text Decoder + Neural Multi-Token Prediction (MTP) speculative decoding (gpuartisan) - Multimodal Vision (visionencoder + visionadapter + endofvision, supporting variable token budgets [70, 140, 280, 560, 1120]) - Multimodal Audio (audioencoderhw Conformer + audioadapter + endofaudio) - gemma-4-12B-it-web-mtp.litertlm - gemma-4-12B-it-web-mtp-vision.litertlm - gemma-4-12B-it-web-mtp-audio.litertlm - gemma-4-12B-it-web-mtp-vision-audio.litertlm

Quantized Gemma 4 31B WebGPU.litertlm bundles for LiteRT-LM Web, with support for: - Text Decoder + Neural Multi-Token Prediction (MTP) speculative decoding (gpuartisan) - Multimodal Vision (visionencoder + visionadapter + endofvision, supporting variable token budgets [70, 140, 280, 560, 1120]) - gemma-4-31B-it-web-mtp.litertlm - gemma-4-31B-it-web-mtp-vision.litertlm

Model · Text generation

ACE-3-26B-A4B-Preview

APMIC

ACE-3-26B-A4B-Preview-260910 is a preview release of APMIC's ACE-3 model family, built for Traditional Chinese (Taiwan) enterprise scenarios and agentic workflows. The model is based on google/gemma-4-26B-A4B-it, a Mixture-of-Experts model with 26B total parameters and about 4B active parameters per token (the "A4B" in the name). APMIC has further optimized it to strengthen: - Traditional Chinese output in Taiwan usage (terminology, phrasing and orthography) The bundled generationconfig.json uses temperature=1.0, topp=0.95, topk=64. These follow the base model's recommended settings. The model can be served with any inference engine that supports Gemma 4 (for example vLLM). Because the…

Model · Image and text to text

ACE-3-F-26B-A4B-260804

APMIC

ACE-3-F-26B-A4B-260804 is an enterprise-grade, production-ready large language model developed and optimized by APMIC for financial and regulated-business scenarios. The model is based on google/gemma-4-26B-A4B-it and has been further optimized through quantization and financial-domain adaptation to support high-reliability deployment in Traditional Chinese business environments. This release demonstrates APMIC’s end-to-end capability in: - Enterprise LLM optimization and deployment engineering - Deployment readiness for private cloud and on-premise AI infrastructures This model is specifically strengthened for finance-oriented prompts and terminology, with stronger alignment - Financial…

Model

bongard-mini

AgentBull

Machine intuition. These selected gameplay recordings show Bongard-mini choosing actions from candidate lists. For board games, the engine supplies legal moves and their computed features; 2048 and Tetris also include engine ratings of moves. A short instruction states the strategy, and the model selects each action. The scores describe these selected recordings with the supplied engine features. Doom — Defend the Center The model receives a text description of the scene every 0.2 seconds and chooses turnleft, turnright or fire. Across 32 episodes capped at 30 seconds, it averaged 10.25 kills, with a best of 20. The GIF shows an excerpt, with probabilities beside the action. Bongard-mini is…

Training runs of the v4 experiments of dramatis, a small research project on small GPT-2-style language models (0.8M–100M parameters) trained on controlled corpora of generated children's stories, looking for signatures of emergent misalignment: how a model builds a "persona" for a class of character names, and how a narrow finetune spreads through it. The experiment plan is docs/2026-09-22EXPERIMENTPLAN.md in the project repository (github.com/kjsatz/dramatis). Preliminary. Runs appear here as they finish on the training machines; results are not yet analysed, checked or published. A paper and a curated release are forthcoming. runs/ /: one directory per pretraining or finetune run…

Model · Text generation

ELF-B-T5Gemma2

Zekai Zhang

ELF-B, a continuous diffusion language model, trained on the embeddings of T5Gemma-2-270M. From the paper Scaling and Distilling Text Embeddings for Better Diffusibility. ELF (Embedded Language Flow) is a continuous diffusion language model that generates a sequence of text embeddings and decodes them to tokens. This model is the unchanged ELF-B trained on OpenWebText-1024 (sequences of 1024 tokens) for 5 epochs at a batch of 512, on the frozen embeddings of the T5Gemma-2 encoder. Sampling uses the SDE sampler with self-conditioning guidance; --sc sets the guidance scale and --nfe the number of steps. With the code of the paper; the checkpoint and the tokenizer are downloaded from this…

Model · Text generation

ELF-B-T5Gemma2distilled

Zekai Zhang

ELF-B, a continuous diffusion language model, trained on the embeddings of T5Gemma-2-270M-OWTdistilled, distilled from T5Gemma-2. From the paper Scaling and Distilling Text Embeddings for Better Diffusibility. ELF (Embedded Language Flow) is a continuous diffusion language model that generates a sequence of text embeddings and decodes them to tokens. This model is the unchanged ELF-B trained on OpenWebText-1024 (sequences of 1024 tokens) for 5 epochs at a batch of 512, on the frozen embeddings of the distilled student T5Gemma-2-270M-OWTdistilled. Sampling uses the SDE sampler with self-conditioning guidance; --sc sets the guidance scale and --nfe the number of steps. With the code of the…

Model · Text generation

ELF-M-T5Gemma2

Zekai Zhang

ELF-M, a continuous diffusion language model, trained on the embeddings of T5Gemma-2-270M. From the paper Scaling and Distilling Text Embeddings for Better Diffusibility. ELF (Embedded Language Flow) is a continuous diffusion language model that generates a sequence of text embeddings and decodes them to tokens. This model is the unchanged ELF-M trained on OpenWebText-1024 (sequences of 1024 tokens) for 5 epochs at a batch of 512, on the frozen embeddings of the T5Gemma-2 encoder. Sampling uses the SDE sampler with self-conditioning guidance; --sc sets the guidance scale and --nfe the number of steps. With the code of the paper; the checkpoint and the tokenizer are downloaded from this…

Model · Text generation

ELF-M-T5Gemma2distilled

Zekai Zhang

ELF-M, a continuous diffusion language model, trained on the embeddings of T5Gemma-2-270M-OWTdistilled, distilled from T5Gemma-2. From the paper Scaling and Distilling Text Embeddings for Better Diffusibility. ELF (Embedded Language Flow) is a continuous diffusion language model that generates a sequence of text embeddings and decodes them to tokens. This model is the unchanged ELF-M trained on OpenWebText-1024 (sequences of 1024 tokens) for 5 epochs at a batch of 512, on the frozen embeddings of the distilled student T5Gemma-2-270M-OWTdistilled. Sampling uses the SDE sampler with self-conditioning guidance; --sc sets the guidance scale and --nfe the number of steps. With the code of the…

Model · Sentence similarity

embeddinggemma-300m-memory-ft-v2

Daecore

An English embedding model for searching notes, procedures, decisions and technical documentation. It maps each query or passage to a normalized 768-dimensional vector and runs locally through ONNX Runtime. Fine-tuning starts from Google's EmbeddingGemma-300M. Version 2 succeeds the first Daecore fine-tune with new weights. Embed queries and passages with the same revision; re-embed stored passages when switching to v2. Install onnxruntime==1.24.4, tokenizers and numpy. Keep model.onnx, model.onnx.data and the tokenizer from the same package together. This CPU example assumes that package is in downloaded-model: Higher cosine similarity means a closer match. Use the query and passage…

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). SFT (QLoRA r=32 on the mixed matura set, no thinking; repo gemma-3-12b-it-matura-history-sft-qlora-r32), then GRPO with Unsloth + TRL on closed exam items with an exact key (single choice, true/false, matching, ordering). Reward = 0.2format + 0.8exact match, Dr.GRPO loss, beta=0 (no KL). THIS VERSION: GRPO step 25 (interim); the full 300-step run replaces it when it finishes. Closed-question exact match on validation (321 items, no judge): 68.2 overall (SFT alone 66.4, base 45.5).…

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). Supervised fine-tuning (QLoRA) of Gemma 3 12B-it on the same mixed set; Gemma 3 has no thinking mode, so teacher traces contribute their final answers only. LoRA r=32, alpha=64, lr 1e-4 cosine, 1 epoch, batch 16, maxlen 6144, Unsloth + TRL Consolidated training set data/trainingdatasets/sfttrain.jsonl (buildsft.py): real CKE papers 2005–2026 with keys, rephrased papers, synthetic image tasks, synthetic full papers, e-podręczniki textbook questions, synthetic Claude/DeepSeek tasks…

static quants of https://huggingface.co/WWTCyberLab/gemma-4-26B-A4B-it-abliterated For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-4-26B-A4B-it-abliterated-i1-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…

Model · Text generation

Gemma-4-E2B-Coder-Uncensored

Minas Fostieris

A code-focused finetune of llmfan46/gemma-4-E2B-it-ultra-uncensored-heretic (Gemma 4 E2B, ~4.6B effective) built specifically for front-end development (React, TypeScript, HTML/CSS) and general Python scripting. Built on an uncensored base, so it just answers the question—no lectures attached. It’s a small model, trained on a single consumer GPU. It writes React components, fixes CSS grid layouts, and won't judge your useEffect dependencies. Measured with lm-evaluation-harness (greedy decoding, temp 0.0, seed 0). Same harness, same conditions for both models. Note: The base model scores higher on pure, edge-case Python algorithmic logic. Hiding it would be weird. This model intentionally…

Model

gemma-4-e2b-it-OptiQ-4bit-decision

MLX Community

gemma-4-e2b-it-OptiQ-4bit turned into a decision model with optiq lora train --decision: a LoRA on the backbone and a new joint schema head that scores noul, choice and score questions in one pass. It runs on Apple Silicon through MLX and OptiQ (optiq serve exposes /v1/systemone). Scored on the full 400-case test split (2,000 decisions) with the benchmark's own metrics. Latency is one request per case with all five questions, on an Apple M3 Max. This model was fitted on the benchmark's own train split and nothing else: 1,080 records, 3 epochs, LoRA rank 16. The test cases are disjoint from it, but they come from the same four workflows, so expect less on decisions of a different kind. The…

Web-optimized gemma-4-E2B-it LiteRT-LM bundles for browser (WebGPU) execution, built with the official conversion pipeline (exportvit, convertermain, litertlmbuildercli). - Multi-signature visionencoder (vision70, vision140, vision280, vision560, vision1120) exported via //thirdparty/odml/generative/modules/gemini/export:exportvit with QAT Int8 weight recovery and query-chunked attention (maxquerychunksize = 630, $k=16$ at vision1120). - Artisan decoder visiontokensnum: 1121 (tokensnum = 1120).

Web-optimized gemma-4-E4B-it LiteRT-LM bundles for browser (WebGPU) execution, built with the official conversion pipeline (exportvit, convertermain, litertlmbuildercli). - Multi-signature visionencoder (vision70, vision140, vision280, vision560, vision1120) exported via //thirdparty/odml/generative/modules/gemini/export:exportvit with QAT Int8 weight recovery and query-chunked attention (maxquerychunksize = 630, $k=16$ at vision1120). - Artisan decoder visiontokensnum: 1121 (tokensnum = 1120).

Research artifact from the Crucible/AfterImage program: a Gemma-4-12B derivative fine-tuned for calibrated abstention -- declining to answer when it lacks the record, instead of confabulating. This is an entertainment model, trained for Tabletop Roleplaying games and chat. Glitter Boy is trained in Adult/NSFW materials and will produce explicit content. Please exercise caution. With ablation, healing and abstention training, guards can sometimes reactivate given the correct context. Try again or tweak prompt or be slightly less naughty. If you managed to trip the guards, you are working extra hard to flood that gate. Reprompt/retry. RAGS/OKF with RPG books to pin hard data or embed data…

weighted/imatrix quants of https://huggingface.co/SubMaroon/Kitchoon-V2-26B-A4B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Kitchoon-V2-26B-A4B-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the…

This repo contains some APEX quantizations of Naphula/Goetia-26B-A4B-v1.7, created using bartowski's imatrix found here. As explained by its creators, APEX is "a novel MoE-aware mixed-precision quantization technique for llama.cpp". I suggest reading their information on the how and why of the method. Quantized using llama.cpp #1692f9e50 For roleplaying, I personally strongly recommend nohurry's SillyTavern presets for Gemma 4 models. My only contribution is compute. This is neither my merge, nor my quantization methodology. Have fun (within the constraints of the license). Google - the base model. Naphula - the Mergelord. Everyone whose finetunes were included in the merge! mudler - for…

The on-device storyteller for Outward, an offline walking adventure. You go outside, find something real ("rainwater running down a drain"), and this model writes the next 60–120 words of the story around it. It runs entirely on the phone, in the browser, with llama.cpp (wllama). Modified by the Outward project. This is a Model Derivative of google/gemma-3-270m-it: fully fine-tuned on 3,186 stories written by a LoRA fine-tuned Qwen3.5-4B teacher (trained on Tinker), then converted to GGUF and quantized to Q40. The eval set has 50 held-out prompts × 3 samples, temperature 0.7, scored with the automatic rubric in the Outward repo: uses the discovery, 60–120 words, safe and outdoors (risky…

Model · Robotics

pi05_mahjong_v1_tray07_twos_dart_noise

Tc Huang

pi0.5 trained on with LeRobot 0.6.1 to pick up, among seven tiles laid anywhere on a foam pad, the mahjong tile an instruction names, and place it in a tray, with an SO-101 arm in the Isaac Lab task Mahjong-Tray7TwosFaces-SO101-v1. Instructions read Pick up the {name} tile and place it in the tray. Trained in simulation only; it has not been run on a real arm. It goes on from the step-002500 checkpoint of which held over the named tile in closed loop. A trace of it found it deciding its descent by its joint state alone: held a few degrees off the hover pose its pushed demonstrations went down from, it went down once given that pose's state, and changed nothing with either camera blacked…

Model

PicoPolite240M-base

Reiwa-AI K.K.

PicoPolite240M is a small-scale language model created using extremely limited computational resources (a single GPU with 32 GB memory) to research training methods for LLMs and SLMs. We will publish a book detailing the entire learning methodology. Furthermore, we will release the complete synthetic dataset created for this purpose. Using the data below, I trained the model for one epoch with a token window of 2000 and fp32 precision; the RoPE θ was set to 3200. Subsequently, using the data below, I trained it for one epoch with a token window of 6400 and bf16 precision; the RoPE θ was set to 10000. Afterward, I applied LongRoPE to extrapolate the token window. This model utilizes google…

OpenArm 양팔 로봇(biopenarmfollower, 카메라 3대, state·action 16차원)의 Redox 시연 200개로 체크포인트 하나가 "task 문장 → 서브태스크 문장 생성 → 그 문장을 조건으로 액션 청크(50스텝)"를 한다. task 문장 (학습에 쓴 것은 이것 하나다): 1. lift the metal plate out of the left beaker 2. move the plate over the blue solution 3. point at the plate with the left hand 4. lower the plate into the blue solution 5. hold the plate still in the solution 6. raise the plate and point at it 7. put the plate into the left beaker 8. return to the home posture - lerobot PR #4184의 브랜치 codex/pi052-language-policy가 필요하다 (학습에 쓴 커밋 3298e15, lerobot 0.6.2). PyPI의 0.6.1에는 pi052 정책도 --interactive도 없다. - 그 커밋의 액션 추론은 그대로는 죽는다: TypeError: PI05Pytorch.embedprefix() takes 5 positional…

在 Dexmal/DM05 上做 LoRA 微调得到的 SO-101 单臂策略： 仿真与真机混成一份，共 3698 集 / 1,280,507 帧 / 10 个任务，全部 30 fps、640×480： - LoRA（all-linear），可训参数 324M / 6.15B = 5.27% - 动作模式 RELATIVE，动作块长度 50 - 等效 batch 48（4 卡 × 每卡 6 × 梯度累积 2），5000 步，bf16，cosine 学习率 成败取环境自带的 issuccess（物体在料箱内、夹爪松开、物体与机械臂都静止），每局上限 500 步： 需要 dexbotic 框架。适配器里记录的底座是 Dexmal/DM05， 完整的数据准备、训练与仿真评测流程见 dexbotic 的 docs/so101.md，教学示例见 适配器随底座 Dexmal/DM05 采用 Gemma 许可。

weighted/imatrix quants of https://huggingface.co/oolabs/sommerfugl-31b-v1 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/sommerfugl-31b-v1-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…

Model

T5Gemma-2-270M-OWTdistilled

Zekai Zhang

A text encoder for continuous diffusion language models (DLMs), distilled from the encoder of T5Gemma-2-270M. It gives the SoTA latent embeddings for continuous DLMs. From the paper Scaling and Distilling Text Embeddings for Better Diffusibility. A continuous diffusion language model generates text embeddings and decodes them to words. T5Gemma-2 provides a strong embedding space for this, but it keeps the words that could fill the same position far apart, and a generated embedding often lands between them and decodes problematically. The student is trained by minimizing the KL divergence between the probabilities that the same frozen T5Gemma-2 decoder predicts from the student's embeddings…

This model is a fine-tuned version of google/embeddinggemma-300m on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 16 - evalbatchsize: 16 - distributedtype: multi-GPU - numdevices: 2 - totaltrainbatchsize: 32 - totalevalbatchsize: 32 - lrschedulertype: linear - trainingsteps: 20000 - Transformers 5.17.0 - Pytorch 2.10.0+cu128 - Datasets 5.0.0 - Tokenizers 0.23.2

An unmodified copy of Gemma3-1B-ITmulti-prefill-seqq4ekv4096.litertlm from litert-community/Gemma3-1B-IT, used by the Ur-Cars-Voice app's on-device chat. Hosted here so the app can download it directly. SHA-256: 1325ae366d31950f137c9c357b9fa89448b176d76998180c08ceaca78bba98be Gemma is provided under and subject to the Gemma Terms of Use found at Use of this model is subject to the By downloading or using this model you agree to those terms and restrictions.

Model · Text generation

WaifuGemma4-26b-a4b-v1

HiWaifu Research

Gemma 4 26B-A4B, post-trained with GRPO against a reward model learned from 1.2 million double-blind votes cast by HiWaifu users inside their own role-play conversations. Put back into the same arena, blind, it met GLM-5.1 in 1,430 battles and won 49.6% of the decided votes; against a 13-model field including Gemini, DeepSeek-v4 and Qwen's character models it won 54.7%. Most open role-play models are tuned on preferences that come from an LLM judge, from a handful of annotators, or from synthetic pairs. We had something rarer: a live arena where, inside ordinary chats on our platform, a user is occasionally shown two candidate replies and asked which one they want to continue with. Those…

weighted/imatrix quants of https://huggingface.co/hiwaifu-research/WaifuGemma4-26b-a4b-v1 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/WaifuGemma4-26b-a4b-v1-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's…