Open-Weight Models

JAX/Flax checkpoints from TanyaoDojo, a from-scratch mahjong AI stack (vectorized env + behavior cloning + self-play RL). Every number below comes from the same duplicate 1v3 protocol: the challenger plays all four seats over identical walls against three copies of a strong open-source baseline (Mortal v4), seedkey=20260711, seeds from 10000, placement points [90, 45, 0, -135]. avgpt is the challenger's mean placement points relative to the baseline; 0 would mean parity. Higher is better. The headline checkpoint has a 100k-game milestone measurement (-4.66 +/- 0.535, 16.0M decisions, zero fallbacks) — not a small-sample estimate. The last row is published deliberately, and its…

Model · Robotics

Task_000004_Peanut_Pick_Place_RLDX_bs8_step10000

Dongyun Kim

Created with Cyclo Intelligence by ROBOTIS.

Model · Robotics

Task_000759_FLOWER_B200_bs8_step5000

Dongyun Kim

FLOWER VLA fine-tuned on the ROBOTIS SG2 Task 000759 LeRobot v3 dataset. The SG2 action/proprioception heads and the six DiT layers absent from the public 12-layer checkpoint are initialized for this fine-tuning setup. The compatible Florence-2 and FLOWER weights are retained. This repository contains a full PyTorch Lightning checkpoint, including model, EMA, optimizer, scheduler, and global-step state. It is intended for offline evaluation and controlled inference integration. It does not authorize robot actuation. Offline MAE will be added after the uploaded checkpoint is downloaded and evaluated with the fixed validation split (5%, seed 242).

This is a trained model of a Q-Learning agent playing Taxi-v3.

GPT-Neo storyteller (nominal 1M; actual 3,745,984 parameters including the 50,257-token embedding) trained on TeenyTinyStories (TTS): 2,491,490 stories (498.5M tokens with EOS) generated by roneneldan/TinyStories-Instruct-33M. batch 1280 x 512, constant LR 5e-4, weight decay 0.1, betas (0.9, 0.95), clip 1.0. - TS-valid capped to stories of at most 400 tokens (20,711 stories): 2.369 / ppl 10.69 Research on small-scale synthetic pretraining data. Generates simple children's stories; sample at temperature 0.8-1.0. See the TeenyTinyStories paper for the corpus recipe and judge evaluations. Apache-2.0.

GPT-Neo storyteller (nominal 33M; actual 68,514,048 parameters including the 50,257-token embedding) trained on TeenyTinyStories (ableian/TeenyTinyStories) batch 1280 x 512, constant LR 5e-4, weight decay 0.1, betas (0.9, 0.95), clip 1.0. - TS-valid capped to stories of at most 400 tokens (20,711 stories): 1.539 / ppl 4.66 Research on small-scale synthetic pretraining data. Generates simple children's stories; sample at temperature 0.8-1.0. See the TeenyTinyStories paper for the corpus recipe and judge evaluations. Apache-2.0.

Model · Feature extraction

TeraAnaly

Tera

Russian speech analysis with one frozen w2v-BERT encoder and independently callable age, gender, emotion, stress and CTC components. Decode audio once, run the encoder once, and reuse its output for any heads you need. Noncommercial use only for the TeraAnaly code and trained heads, under CC-BY-NC-SA-4.0. The original encoder weights retain their upstream CC-BY-4.0 license. See LICENSE.md. Outputs are an integer age in years, the highest gender label, the highest emotion label, and a transcript with + before stressed vowels. Emotion labels are neutral, angry, positive, sad, other; demographic labels are female, male, child (child is an age category inherited from the teacher).…

Model · Text generation

Terminal-12k-bottom80

Dang Cao Cuong

This model is a fine-tuned version of /helios-storage/helios4-data/cuong/Terminal-complete8k on the nemotroncompletebottom8012k dataset. The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 1 - evalbatchsize: 8 - distributedtype: multi-GPU - numdevices: 4 - totaltrainbatchsize: 4 - totalevalbatchsize: 32 - lrschedulertype: cosine - numepochs: 2.0 - Transformers 5.6.0 - Pytorch 2.11.0+cu130 - Datasets 4.0.0 - Tokenizers 0.22.2

weighted/imatrix quants of https://huggingface.co/shunzou05/TerminalHorizon-122B-A10B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/TerminalHorizon-122B-A10B-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…

Model · Text generation

Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF

Josh Bolding

Refusal-ablated Ternary Bonsai 2 27B, edited directly on the ternary lattice and shipped in PrismML's native PTQ10 pack. - 5,946,648,928 bytes — byte-for-byte the size of the official PTQ10 release - No requantization, no BF16 bake, no runtime steering, no control vector at serve time - Requires the PrismML llama.cpp fork Differs from PrismML's release in exactly 98 tensors and nowhere else. The other 753 tensors are byte-identical, including tokenembd and output. Anyone with both files can check that without trusting us. Paired against the untouched PrismML release: same card, same runtime, same flags, same seed, enablethinking: false on both arms. Judge is Qwen3.8-27B-OBLITERATED-Q80 with…

A Satellite build of Ternary-Bonsai-2-27B-Heretic. A Qwen3.5-hybrid 27B fine-tuned by LoRA decision-distillation against the laya compaction policy, so that it emits an explicit compaction decision before it answers. This is a text-only model. It has no vision encoder and makes no image claims. Given a conversation transcript, the reply begins with a strict JSON decision block, then the literal marker ---decision-end---, then a normal answer: The decision is a redundancy judgement, not a length threshold. A short but repetitive transcript earns yes; a long information-dense one can earn no. Decoded on 9 held-out windows from sessions used in training, greedy, via llama-server on the F16…

Model · Text generation

Ternary-Bonsai-2-27B-Refusal-Steering-GGUF

Mithril

Experimental refusal-direction control vector for This repository does not contain a fully uncensored model. It contains a 1.3 MB GGUF control vector and the reproducibility material used to test refusal steering. The held-out evaluation did not support a reliable uncensored claim, so this artifact is published under its measured scope. normalized independently for layers 1–63 - At -2.0 one training prompt changed internal reasoning toward conditional compliance, but its final answer still refused - At -3.0 over layers 10–63 output quality collapsed - At -3.0 over layers 20–40 benign arithmetic remained correct (17 x 23 = 391), but 4/4 held-out prompts still refused These are small…

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at less than two-thirds of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at…

Bonsai 2 27B by Prism ML, repacked for vLLM. Unofficial; not affiliated with Prism ML. It needs the prismternary vLLM plugin from fraserprice/bonsai-vllm, which has the run command, kernels and throughput numbers: Built and tested for the RTX PRO 6000 Blackwell only; other NVIDIA GPUs are untested. Problems: open an issue. - The ternary weights of the MLX pack, bit for bit: the same 2-bit codes and FP16 group scales (g128), in the same Hadamard-rotated basis. MLX's redundant per-group biases (-scale) are dropped, and the rotation signs move into config.json. - The embedding table is dequantized to BF16. - Norms and the linear-attention state path are Prism ML's own tensors from the MLX…

Model · Image and text to text

Ternary-Bonsai-2-4B-onwx

Ryu Gyo

Prism ML の Ternary-Bonsai-2-4B（Qwen3.5-4B を三値の重みで学習し直したモデル）を、onwx 用に変換したものです。onwx は LLM を AMD Ryzen AI の NPU（XDNA2）だけで 動かすアプリで、このリポジトリにはモデルと、このモデル専用の NPU プログラムが入っています（アプリは別にインストールします）。 重みは三値（−1・0・+1）を 2 ビットのまま NPU に載せ、行列計算・DeltaNet・アテンション・LM ヘッドまで 1 トークンの計算をすべて NPU の 32 個の AI エンジンで行います。同じ大きさの int4 のモデルよりダウンロードもメモリも小さく、生成も速くなります。画像のエンコーダー（ViT）は CPU で動きます。NPU 向けのプログラムはビルド済みなので、PC の上でコンパイルを待つことはありません。 （onwx 0.7.0、Ryzen AI Max+ 395（Windows）で NPU の電力モードを performance にして測定。Ryzen AI 300 シリーズ（HX 370 など）も NPU は同じ 32 個の AI エンジンで、同じ方式で動きます。標準の電力モードでは NPU のクロックが下がって 2 割ほど遅くなります。電力モードは管理者の PowerShell で C:\Windows\System32\AMD\xrt-smi.exe configure --pmode performance。Windows の Copilot+ の AI 機能が NPU…

static quants of https://huggingface.co/jonathan-kellerai/Ternary-Bonsai-2-9B-hf-bf16 For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. 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…

Model · Image and text to text

Ternary-Bonsai-2-9B-onwx

Ryu Gyo

Prism ML の Ternary-Bonsai-2-9B（Qwen3.5-9B を三値の重みで学習し直したモデル）を、onwx 用に変換したものです。onwx は LLM を AMD Ryzen AI の NPU（XDNA2）だけで 動かすアプリで、このリポジトリにはモデルと、このモデル専用の NPU プログラムが入っています（アプリは別にインストールします）。 重みは三値（−1・0・+1）を 2 ビットのまま NPU に載せ、行列計算・DeltaNet・アテンション・LM ヘッドまで 1 トークンの計算をすべて NPU の 32 個の AI エンジンで行います。同じ大きさの int4 のモデルよりダウンロードもメモリも小さく、生成も速くなります。画像のエンコーダー（ViT）は CPU で動きます。NPU 向けのプログラムはビルド済みなので、PC の上でコンパイルを待つことはありません。 （onwx 0.7.0、Ryzen AI Max+ 395（Windows）で NPU の電力モードを performance にして測定。Ryzen AI 300 シリーズ（HX 370 など）も NPU は同じ 32 個の AI エンジンで、同じ方式で動きます。標準の電力モードでは NPU のクロックが下がって 2 割ほど遅くなります。電力モードは管理者の PowerShell で C:\Windows\System32\AMD\xrt-smi.exe configure --pmode performance。Windows の Copilot+ の AI 機能が NPU…