전체 검색

AI 모델 85003

• LFM2.5-2.6B-GGUF-shards↗

  Arki05

  - `source/`: LiquidAI's BF16 GGUF (LiquidAI/LFM2.5-2.6B-GGUF), unchanged. - `types/ -hq.gguf`, `types/ -hq1.gguf`: the tensors at llama.cpp type `T`, rebuilt from the BF16 weights in two Hessian-quantized (GPTQ-family) builds: `-hq`, the higher-quality one, the block tensors; `-hq1`, the first build, every quantized tensor. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `data/`: the calibration data the types were made from (token ids and their manifest). - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The first version of this store (bartowski's BF16 GGUF and imatrix, types by llama.cpp's `llama-quantize`) is at revision `fe50613`.

• Art-v0-3B-GGUF↗

  bartowski

• Qwen2.5-Coder-1.5B-Instruct-abliterated-GGUF↗

  bartowski

  Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

• starcoder2-7b↗

  bigcode

  1. Model Summary 2. Use 3. Limitations 4. Training 5. License 6. Citation StarCoder2-7B model is a 7B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3.5+ trillion tokens. - **Project Website:** bigcode-project.org - **Paper:** Link - **Point of Contact:** contact@bigcode-project.org - **Languages:** 17 Programming languages

• Drjajsufhfh↗

  Bill435

• FLUX.1-schnell-onnx↗

  Black Forest Labs

• bert-base-arabic-camelbert-da↗

  CAMeL-Lab

• madlad400-3b-mt-GGUF↗

  cstr

  MADLAD-400 is a 3B-parameter T5-based multilingual machine translation model covering **450+ languages**, trained on 1 trillion tokens. It was developed by Google and achieves strong results across a wide range of languages, with special emphasis on low-resource and underrepresented languages. Distributed under **Apache 2.0 license**. MADLAD-400 supports over 450 languages using ` ` target language tags (ISO 639 codes). This includes all major world languages plus many low-resource languages. See the original model card for the full language list.

• Qwen3.5-27B-AWQ-BF16-INT4↗

  cyankiwi

• XORTRON-RICO-v3-GGUF↗

  darkc0de

  This model has achieved the highest CEA-100 Criminal Enablement Assessment score of any Qwen 3.8 27B model I’ve tested to date. This is a linear merge of: - `darkc0de/RICO` (orcarouter/Qwen3.8-27B-Uncensored finetuned on XORTRON SFT Data) - `darkc0de/RICO-v2` (DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU finetuned on XORTRON SFT Data) Thinking: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0