전체 검색
AI 모델 2119
- Huihui-Qwen3.8-27B-abliterated-GGUF↗
AI-conn
> **This is a fork, not our model.** All credit for the abliterated build goes > to **huihui-ai**, > and for the base model to **Qwen (Qwen/Qwen3.8-27B)**. > This fork exists so the fleet's copy cannot be altered or pulled upstream, > and to carry the fit notes below. License: Apache-2.0 (per the source repo). The build was made by **abliteration** (refusal-direction removal, using Sumandora's remove-refusals-with-transformers) — the method and tool are documented on the source card. Note from the same card: several sub-series (Swift / Saluki / Ternary variants) ablate only layers 22–52; the headline UD-DW and plain series are the main line. **Recommended file for a 20 GB card:** `Huihui-Qwen3.8-27B-abliterated-UD-DW-Q4_K_M.gguf` (15.41 GiB).
- StartLux-Decision-v1-9B-Q8_0-GGUF↗
startlux-models
"Same decision" is the share of the 231 public JevBench items on which the file picks the same answer as the original weights run through the `startlux_decision` package, with the same prompts, readout and temperatures. Q8_0 and Q4_K_M are llama.cpp's standard quantizations of BF16, without an importance matrix. `-ngl 99` puts every layer on the GPU (CUDA or Metal); leave it out on a CPU-only machine. llama.cpp has to be recent enough for this model (build b10454 or newer). Plain chat with a GGUF file does not give these decisions: the option-letter readout and the per-type temperatures live in `gguf_server.py`, not in the weights. The file holds the text decoder only.
- slimsam-50-uniform↗
Xenova
https://huggingface.co/nielsr/slimsam-50-uniform with ONNX weights to be compatible with Transformers.js. Next, select the channel with the highest IoU score, which in this case is the second (green) channel. Intersecting this with the original image gives us an isolated version of the subject: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
- neural-super-sampling↗
Arm
- nemo-nano-codec-22khz-1.89kbps-21.5fps↗
NVIDIA
The NeMo NanoCodec is a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to achieve state-of-the-art audio compression across different bitrate and frame rate ranges. Model variant details: Model | Sample Rate | Frame Rate | Bit Rate | # Codebooks | Codebook Size | Embed Dim | FSQ Levels | :-----------:|:-----------:|:----------:|:----------:|:-----------:|:-------------:|:-----------:|:------------:| 1.78kbps-12.5fps| 22050 | 12.5 | 1.78kpbs | 13 | 2016 | 52 | [8, 7, 6, 6] | 0.6kbps-12.5fps | 22050 | 12.5 | 0.6kpbs | 4 | 4032 | 16 | [9, 8, 8, 7] | 1.89kbps-21.5fps | 22050 | 21.5 | 1.89kpbs | 8 | 2016 | 32 | [8, 7, 6, 6] | ⚠️ **Note on 0.6kbps-12.5fps** This variant is designed for **fine-tuning with a limited set of speakers**, as shown in our S2S Duplex paper. It is **not recommended** for general-purpose audio encoding or decoding.
- samantha-1.1-MBX-7B-i1-GGUF↗
mradermacher
- Topxtral-4x7B-v0.1↗
MaziyarPanahi
There are three killers in a room. Someone enters the room and kills one of them. Nobody leaves the room. How many killers are left in the room? Explain your reasoning step by step. Mark is faster than Mary , Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step If I lay 2 wet shirts out in the sun flat on the ground to dry and it takes 5 hours until they are dry, how long would it take to dry 4 shirts of the same type that way simultanously?
- Samantha-qwen-0.5b-GGUF↗
mradermacher
- DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF↗
richardyoung
GGUF quantizations of richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic, an abliterated build of deepseek-ai/DeepSeek-R1-0528-Qwen3-8B (DeepSeek's R1-0528 reasoning distilled into Qwen3-8B: a reasoning model that emits chains before answering) made with Heretic. The very low KL divergence (0.041, far below the 0.5 “damage” threshold) means the model retains essentially all of its original capabilities and coherence. Each quant compared with the F16 model using `llama-perplexity --kl-divergence` on the wikitext-2 test set (40 × 512-token chunks). KL divergence measures how far the quant's next-token probabilities drift from F16; lower is better. Top-token match is how often the quant picks the same next token as F16. As a rough guide, a KLD under 0.01 is hard to tell from F16, and from about 0.05 differences start to show in longer outputs.
- urdu-sentiment-model↗
Ahsamkk