Open-Weight Models Under Apache License 2.0

Model · Image and text to text

ancient-words-o1-gguf

Rengo Syrup

GGUF files of commreteris/ancient-words-o1 for llama.cpp. The model reads a scanned book page and returns its regions and every word, each with a polygon, as one JSON object. The prompt, output format, training and evaluation are described in that repository's model card. Both files are needed. They were converted from the float32 weights with llama.cpp 0c1e570 (converthftogguf.py --outtype q80 --no-mtp, and --mmproj --outtype f16). Qwen3.5 support needs a llama.cpp build from that commit or later. The fine-tuned checkpoint has no multi-token-prediction head, so these files cannot be used for MTP speculative decoding. llama.cpp needs a Hugging Face token with read access in HFTOKEN. The…

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps). Use the token vxy girl to invoke the concept.

Model · Text to speech

antalia-mini-web-onnx

Fr0stb1rd

ONNX-converted weights of cloud0day3/antalia-mini for in-browser inference (produced by fr0stb1rd/antalia-mini-web). - textstage.onnx: text → character features + durations - soundstage.onnx: DiT Flow-Matching generator → mel frames - decoder.onnx: Vocos ConvNeXt vocoder → 48 kHz waveform - foreigndict.json: CMU English to Turkish phonetic dictionary (80k+ words) - foreignparts.json: CamelCase part respellings for brand words (37k entries) - knownwords.json: frequent Turkish words (anti-respell shield, 6k entries) - englishi.json: dotted/dotless I decision list for English words (14k entries) The models in this repository are licensed under the Apache License 2.0. This software comes with…

Model · Text generation

antcoder-builder-7b

Deep Das

Engineered by Deep Das • Part of the AntCoder Multi-Agent Coding Suite AntCoder-Builder-7B is a high-precision LoRA adapter fine-tuned on top of Qwen/Qwen2.5-Coder-7B-Instruct. It is specifically optimized to perform Contract-to-Implementation synthesis for complex, production-grade TypeScript applications. Given a strict TypeScript interface, class signature, function type contract, or JSDoc specification, AntCoder-Builder synthesizes the complete, strictly-typed implementation without type errors, missing properties, or hallucinated APIs. - Zero-Stub Completions (99.4%): Completely eliminates lazy // TODO, /... /, or throw new Error("not implemented") placeholders commonly emitted by…

Model · Text generation

antcoder-fixer-7b

Deep Das

Engineered by Deep Das • Part of the AntCoder Multi-Agent Coding Suite AntCoder-Fixer-7B is a specialized LoRA adapter fine-tuned on Qwen/Qwen2.5-Coder-7B-Instruct. It solves the single hardest problem in autonomous coding agents: hallucinatory patching and compile loops. Unlike generalist models that attempt to rewrite entire 500-line source files (frequently breaking unrelated functions or losing imports), AntCoder-Fixer acts as a surgical precision tool: 1. It ingests the exact TypeScript compiler diagnostic (e.g. TS2339: Property 'user' does not exist on type 'Session'). 2. It ingests the local 20-line source context window. 3. It emits a minimal, standard Git Unified Diff patch (…

static quants of https://huggingface.co/legmlai/apertus-8b-swiss-insurance 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

Apodex1.1-mini-Ciru-Halo-Agent-vllm-strix-halo

Ciru - Crown

Ciru v4.1.2 — October 5, 2026. Applies the shared output-budget correction; Apodex retains its own native MTP4 implementation. Explicit 262,144-token output ceilings now use the fully rendered prompt's remaining context. Weights, pinned engine wheels and sampling defaults are unchanged. Patch notes · Upgrade existing installations. OMP clients must advertise input: [text, image], reasoning: true, contextWindow: 262144 and maxTokens: 262144 to use vision and the full output ceiling. Ciru v4.1.1 — September 30, 2026. Qualified repairs and a retained subset of community PR #2. Apodex retains its own native MTP4, model-specific state layout and released recurrence/attention implementation. The…

Model · Text generation

APUS-OpenJev-v1-35B-A3B

APUS AI

A Qwen3.5 MoE decision model for choosing browser actions, selecting workflow steps, and judging natural-language criteria. Give the model a shared state and a set of candidate actions; the included decision runtime returns a distribution over those candidates. This repository contains 35B-A3B checkpoint-5949 merged BF16 weights. It is a standalone model with root-level Hugging Face configuration and weights, requiring no separate LoRA adapter. The native merged model scores 71/80 (88.75%) at its full 40-layer depth on the Frozen80 development panel. The decision interface accepts 2–16 request-specific candidates. Applications can use the returned candidate IDs to dispatch actions or build…

wikimedia/wikipedia - epfml/FineWeb2-HQ pipelinetag: text-generation - arabic - gpt2 - pretraining

Model · Speech recognition

ARK-ASR-0.6B-GGUF

Max Farrell

Community Q8 conversion of Edge0/ARK-ASR-0.6B, prepared for a draft Hex integration. No retraining. Not affiliated with the original authors, and not a canonical handy-computer artifact. Requires an ARK-enabled runtime. Stock llama.cpp, whisper.cpp and released transcribe-cpp 0.2.4 cannot load it. Use the candidate runtime at revision 19f301609c06126e5071d1de5acdd95c714eec05. ark-asr-0.6b-Q80.gguf: 1,372,881,664 bytes. SHA-256: ceca6bacd9cab3b52892de6703562aeeb62dc8a4b14aab0b020706637dd127dc. The 0.6B name describes the decoder; the full model also contains the audio encoder and adapter. Q8 linear weights, F16 tied embedding/output matrix and convolutions, F32 norms/biases/frontend tensors.…

weighted/imatrix quants of https://huggingface.co/0XARTEX/artex-coder-7b For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/artex-coder-7b-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: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Quantized graphs for the browser runtime: - llmint4/ - Qwen3.5-0.8B + ASMR LoRA, merged and exported, MatMulNBits int4 - ttsint4/ - F5-TTS DiT step + vocoder, int4 MatMul, convs in session dtype llmfp16/ and ttsfp16/ hold the fp16 exports they were quantized from.

static quants of https://huggingface.co/allenai/AstaBrief8B For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/AstaBrief8B-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: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

weighted/imatrix quants of https://huggingface.co/allenai/AstaBrief8B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/AstaBrief8B-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: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

AstralLM is a compact, efficient causal language model built for Hugging Face Transformers. It features a clean decoder-only transformer architecture with Grouped Query Attention (GQA), SwiGLU feed-forward networks, RoPE positional embeddings, and per-head QK-norm — delivering strong performance at a small parameter count (~138M). AstralLM is a decoder-only transformer with the following design choices: The model uses 8 query heads and 4 key/value heads (2:1 ratio), halving the KV cache memory footprint during inference without measurable quality degradation. Each head operates over a head dimension of 80. Per-head RMSNorm is applied to both query and key projections before the rotary…

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 32 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 32 - lrschedulertype: linear - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2

Model · Speech recognition

Audio8-ASR-Infinite

Edge0

Audio8 ASR Infinite is a native streaming speech recognition model built to be as responsive as possible. It offers a selectable audio clock (80/120/160 ms) and a transcription delay (240–560 ms). With our adapted vLLM build it transcribes unlimited-length audio 24/7 without drifting. - Super responsive — the native streaming architecture decodes 12.5 times per second. - Unlimited-length transcription — a rolling KV Cache keeps both memory and latency constant, even in 24/7 operation. - Selectable streaming clock — one text token per clock step (12.5 / 8.3 / 6.25 decisions per second), balancing perception granularity and resource cost. - Configurable transcription delay — set how much…

Model · Image and text to text

Aura-Prototype-26B-A4B

EldritchLabs

This is a merge of pre-trained language models created using mergekit. This model was merged using the aura merge method. Aura is an experimental method with a live heatmap visualizer. This model took 10 hours to merge using graphv18.py The following models were included in the merge: - TheDrummer/Orion-26B-A4B-v1.1 - Gryphe/Pantheon-Reasoning-26B-A4B-1.1-V2 - electroglyph/gemma4-26b-fiction-bf16 The following YAML configuration was used to produce this model

On-device TFLite conversion of the glintr100.onnx face recognition model from fal/AuraFace-v1 (Apache-2.0). Only the recognition model is included. The other files bundled in the AuraFace repo (scrfd, 2d106det, 1k3d68, genderage) are InsightFace models under a non-commercial license and are not part of this repository. - Converted ONNX (NCHW) → TFLite (NHWC) with onnx2tf, batch fixed to 1. - Cosine similarity to the original ONNX embedding on aligned real faces: mean 0.998. AuraFace-v1 by fal.ai, licensed under the Apache License 2.0. See LICENSE.

Native audio in, structured decisions out. Aural One adapts Gemma 4 E2B to score supplied choices from a recording, a written state, and named questions. One model handles the audio and the decision; its inference path does not require speech-to-text or a separate sound classifier. This v0.1.0 research preview publishes a frozen adapter and 54.3 million updated acoustic/projection weights. The pinned Gemma 4 E2B base is downloaded separately. The language model was frozen during this final training stage. These numbers have different test scopes. The full evaluation report covers the frozen reference, listener-vote cross-entropy and calibration, same-words contrasts, sound events…

Model · Text classification

auto-200m-2-int4

SSH

This is auto-200m-2 with its weights stored as 4-bit integers. The file is 77 MB instead of 299 MB, about a quarter of the size. It gets 2,884/3,000 on the benchmark, with 60 false approvals and 56 false denials. The BF16 model gets 2,890, with 53 and 57. 44 of the 3,000 decisions differ from the BF16 model. auto-200m-2 is a 149.6M-parameter ModernBERT classifier. It reads an AI agent's proposed tool call, the user's request and the agent's history, then answers approve or deny. It takes up to 65,536 tokens of context. This version loads through one small Python file, autoquant.py, in plain PyTorch, without compiled kernels. It was checked on NVIDIA CUDA, the Apple M4 Max CPU and Apple MPS.…

Model · Text classification

auto-200m-2-int8

SSH

This is auto-200m-2 with its weights stored as 8-bit integers. The file is 150 MB instead of 299 MB, and it gets the same benchmark score: 2,890/3,000, with 53 false approvals and 57 false denials. Only 2 of the 3,000 decisions differ from the BF16 model. auto-200m-2 is a 149.6M-parameter ModernBERT classifier. It reads an AI agent's proposed tool call, the user's request and the agent's history, then answers approve or deny. It takes up to 65,536 tokens of context. This version loads through one small Python file, autoquant.py, in plain PyTorch, without compiled kernels. It was checked on NVIDIA CUDA, the Apple M4 Max CPU and Apple MPS. For an even smaller file, see auto-200m-2-int4 (77…

Model · Sentence similarity

AX-Qwen3-Embedding-0.6B-CUDA-AXQ-NVFP4-W4A4

AutomatosX

AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and…

Model · Sentence similarity

AX-Qwen3-Embedding-4B-CUDA-AXQ-NVFP4-W4A4

AutomatosX

AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and…

Model · Sentence similarity

AX-Qwen3-Embedding-8B-CUDA-AXQ-NVFP4-W4A4

AutomatosX

AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and…

Model · Text generation

Aztec-Coder-4B-GGUF

Prithiv Sakthi

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp

Model · Robotics

b1k-2026-3more-ft1

Rena Tian

Selected checkpoint for the BEHAVIOR-1K 2026 submission. (IliaLarchenko/behavior-1k-solution, ~3B params, task-ID embeddings, no language prompt). - Checkpoint is params-only (no optimizer state): it can be served or used as an init, not --resumed. - params/ — orbax/ocdbt parameters - assets/b1k20263moretasks/normstats.json — normalization stats - CHECKPOINTMETADATA Serve with scripts/serveb1k.py --task-id 56 policy:checkpoint --policy.config pibehaviorb1k20263more --policy.dir (use --task-id 78 for task 78). Scored the 2026 leaderboard way: public instances 0-9 (ids 301-310), one rollout each, default 1.5x timeouts, task score = sum / 10. - Use this checkpoint for tasks 56 and 78. For task…

Model · Robotics

b1k-2026-task20-ft1

Rena Tian

Selected checkpoint for the BEHAVIOR-1K 2026 submission. (IliaLarchenko/behavior-1k-solution, ~3B params, task-ID embeddings, no language prompt). - Checkpoint is params-only (no optimizer state): it can be served or used as an init, not --resumed. - params/ — orbax/ocdbt parameters - assets/b1k2026task20/normstats.json — normalization stats - CHECKPOINTMETADATA Serve with scripts/serveb1k.py --task-id 20 policy:checkpoint --policy.config pibehaviorb1k2026task20 --policy.dir. Scored the 2026 leaderboard way: public instances 0-9 (ids 301-310), one rollout each, default 1.5x timeouts, task score = sum / 10. - Checkpoint choice, screened on held-out instances 311-315 (mean q): step 8000 =…

Params-only checkpoints for offline evaluation. trainstate is not included, so these cannot be resumed from — inference/eval only. Single-task fine-tune of the 2025 winner's checkpoint2 (the official checkpoint covering task 1) on task 1 = pickinguptrash, using the 200 human demos plus 788 scripted recovery episodes from fastwalker1118/B1kRecovery (task1/Demo+Recovery). Planned 5 epochs; these are the checkpoints nearest the epoch boundaries (one epoch = 15,089 steps). actionloss is training-set loss only (no validation split, no rollouts yet). Single-task fine-tune of the 2025 winner's checkpoint1 (the official checkpoint covering task 2) on task 2 = puttingawayHalloweendecorations, using…

Model · Image and text to text

Baanzon-33street-3.8-27B-Uncensored-Aggresive-MTP-GGUF

Opraiz Technology

GGUF distribution of the 27B vision-language model with an aggressive, uncensored behavioral profile, featuring multi-token prediction (MTP) speculative decoding acceleration for fast inference in llama.cpp. - Uncensored / aggressive personality — minimal refusals, combative direct tone - Multimodal (image + text) — vision projector included (mmproj), supports image input - MTP speculative decoding — token-drafting heads for substantially faster generation - Long context — 262,144-token context window (32K-tuned FastMTP variant included) - Multilingual — English / Chinese / multilingual - Quantized for local inference — ready-to-run GGUF quants, no PyTorch weights required All files are…

Model · Tabular classification

BAAR4-guard

BAAR

이 저장소는 2017~2026 전주기 트래픽(CIC-IDS2017, CICDDoS2019, CICIoT2023, 2024~2026 AI Vectors)으로 훈련된 고속 인라인 AI 보안 방화벽 엔진입니다. 1. model.safetensors: PyTorch SafeTensors 가중치 2. model.onnx: WebAssembly 및 에지 런타임용 고속 ONNX 그래프 3. modelguardultrafp16.baar3: Zero-Copy Direct-mmap FP16 초고속 커널 바이너리 4. config.json: Robust 스케일러 및 제로 트러스트 임계치 메타데이터

Model · Text generation

Baihua-Gemma4-E4B

Roland Wayne

Conversational Writing Model｜口语化写作模型 Baihua-Gemma4-E4B 白话 Baihua 是Roland Wayne基于 Google Gemma 4 E4B-it 经过后训练的中文口语化写作模型。把已有内容，或整理好的事实、观点和提纲，写成像人类口述的正文，减少模板化、机械化的表达。 Roland Wayne 是内容创作者，也是白话 Baihua 的训练作者。在这个项目中，他负责确定表达目标、筛选训练材料，并通过实际测试和人工修改评估模型输出。 X：https://x.com/rwayne Github：https://github.com/ozrwayne - 微调方法：LoRA，rank 16，alpha 32；在前一轮风格 adapter 基础上继续进行配对微调。 - 完整权重：BF16 Safetensors，LoRA 已合并，加载完整权重时不需要再叠加同一 adapter。权重文件合计约 15.88 GB；含配套文件的完整包约 15.91 GB（十进制）。 - Ollama 性能测试使用约 14.94 GB 的 BF16 文本 GGUF 运行副本，归一化等少量张量为 FP32；它不包含纯文字推理不需要的音频和图像编码模块。原完整 Safetensors 模型保持独立。 - E4B 是基础模型的官方规格名称，不表示总参数只有 4B。官方标注约 4.5B 有效参数、含嵌入约 8B；当前 Ollama 文本副本实测为 7,463,013,674 个参数，约 7.5B。 - 配置总上下文：131,072…

This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.

Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct, merged and quantized to q4KM. The Modelfile pins the system prompt and this decoding: 920 held-out commands Judge columns are claude-sonnet-5 scoring a fixed 200-command subset. Apache-2.0, matching the base model, whose weights this GGUF contains. Training data comes from the nl2bash project; consult it for the terms attached to that corpus.

Model

beit-checkpoint

Yang

Working implementation of Beit for Classification using a base configuration. The repository focuses on transparent code and repeatable smoke tests; benchmark claims are deliberately omitted. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses rmsprop with a onecycle schedule. These are starting values in the script, not evidence of a…

Model

beit-finetuned

Matthew F. Thomas

This repository is a compact, custom PyTorch implementation of Beit for Contrastive. The nano configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adam with a linear warmup schedule. These are…

π₀.₅ (Pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository. This policy has been trained and pushed to the Hub using LeRobot. Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and…

Full fine-tuning of bert-base-uncased for 4-class news topic classification, delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a linear classification head on top of the [CLS] token's last hidden state, mapping to 4 topic classes: World, Sports, Business, Sci/Tech. - 10% of the official train split was held out as validation; the official test split was left untouched. - 4 balanced classes. Two adaptation methods were trained and compared; full fine-tuning is the delivered model, since it beat the feature-based baseline by a margin well above the run-to-run noise floor (±1–3 points…

Model · Token classification

bert-base-cased-pos-tagging-ewt

Angel Rivaldo Canche Chuc

Modelo bert-base-cased ajustado finamente (Fine-tuned) para la tarea de Part-of-Speech (POS) Tagging utilizando las 17 etiquetas universales (UPOS) del dataset universal-dependencies/universaldependencies (configuración enewt). Etiquetado Morfosintáctico Automático: Clasificación de categorías gramaticales (Part-of-Speech Tagging) en oraciones en idioma inglés. Análisis Lingüístico: Extracción de características sintácticas para sistemas downstream de NLP, desambiguación léxica y procesamiento del lenguaje. Parameter Groups (Método 1 - Partial): classifier: Learning Rate 1e-3 bert.encoder.layer.10 y layer.11: Learning Rate 2e-5 Parameter Groups (Método 2 - Full Ganador): classifier…

Model · Question answering

bert-base-cased-squad-extractive-qa

Russel Ku

This repository provides a fine-tuned bert-base-cased model adapted for the downstream task of Extractive Question Answering on the full SQuAD v1.1 dataset. Given a (Question, Context) pair, the model predicts the exact start and end character/token spans within the context passage that answer the question. The model was evaluated on the complete SQuAD v1.1 validation set (valdataset, 10,570 examples): Our final Epoch 3 checkpoint achieves 88.21% F1 and 80.75% EM, matching the original Google BERT benchmark (-0.29 F1 points) with complete reproducibility on modern GPU hardware and AMP FP16. - Sequence Length (maxlength): 384 tokens - Document Stride (docstride): 128 tokens To better…

token-classification - bert - ner - lhoestq/conll2003 - precision - recall pipelinetag: token-classification basemodel: bert-base-uncased Fine-tuning of bert-base-uncased for Named Entity Recognition (NER), delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a token-level linear classification head over the last hidden state of every token, predicting one of 9 BIO-scheme entity tags (person, organization, location, miscellaneous, or none). (lhoestq/conll2003), using its own official train/validation/test splits. split a word into multiple subwords, the label is placed on the first…

Fine-tuning of bert-base-uncased for extractive Question Answering, delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a qaoutputs head that predicts, per token, the probability of being the start and the end of the answer span within the given context. (rajpurkar/squad), subsampled to 15,000 examples from the official train split (as required by the assignment), with a 90/10 split used for training/ validation. SQuAD's official validation set (10,570 questions, never seen during training) was reserved as the final test set. - Preprocessing uses a sliding window (stride) since…

Fine-tuning of bert-base-uncased for Part-of-Speech (POS) tagging, delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a token-level linear classification head over the last hidden state of every token, predicting one of 17 Universal POS (UPOS) tags (NOUN, VERB, ADJ, DET, PUNCT, etc.). (universal-dependencies/universaldependencies, config enewt). (universaldependencies/universaldependencies) has a typo; the correct organization name on the Hub uses a hyphen (universal-dependencies). - Same per-token label shape as NER, so the same subword-alignment convention is used: the label goes…

static quants of https://huggingface.co/ProCreations/BetterWright-K2-Horizon-7B-Uno For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants are available at https://huggingface.co/mradermacher/BetterWright-K2-Horizon-7B-Uno-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…

A System One decision model with open weights. Give it a document (text, email, ticket, log or JSON) and typed questions; it returns typed answers (yes/no, a choice between options you describe, or a score on levels you define) with a calibrated probability for every option, in one pass. It never generates text, so there is nothing to parse and nothing to hallucinate. It runs on your own machines: your documents never leave them. About 26B parameters, built on Google Gemma 4 26B-A4B (mixture of experts, about 4B active per token). Everything it needs is in this repository, so nothing else is downloaded. English text, up to 4,096 input tokens; needs one GPU with about 60 GB of memory (bf16).…

Bielik-11B-v3.0-Instruct post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of speakleash/Bielik-11B-v3.0-Instruct. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

Bielik-11B-v3.0-Instruct post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of speakleash/Bielik-11B-v3.0-Instruct. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.