サイト内検索
AI モデル 84761
- Heimer-kto-TinyLlama-1.1B-GGUF↗
tsunemoto
- fine-tuned-nsfw-classification↗
umairrkhn
This model is a fine-tuned version of Falconsai/nsfw_image_detection on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0000 - Accuracy: 1.0 The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 4
- FLUX.2-klein-9B-ComfyUI↗
unsloth
- Llama-3.1-8B-Instruct-FP8-Dynamic↗
unsloth
- Qwen3-32B-GGUF↗
unsloth
See our collection for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats. Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. - Fine-tune Qwen3 (14B) for free using our Google Colab notebook here! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. - Run & export your fine-tuned model to Ollama, llama.cpp or HF.
- Qwen3.6-35B-A3B-Uncensored-GGUF↗
xCloudinfo
以 **Qwen/Qwen3.6-35B-A3B**(qwen3_5_moe混合線性注意力MoE + reasoning,35B總/3B活躍)為底, 經 **abliteration(拒絕方向正交化)** 降低過度拒絕的版本,GGUF量化格式,由 **xCloudinfo(云碩科技)** 釋出。 > **使用前提:本模型僅供在合法、不違法的前提下使用** —— 授權範圍內的資安研究、紅隊測試、內容審核研究、 > 學術研究,以及減少模型「過度拒絕」造成的可用性問題。**使用者須自行為其用途負全部法律與道德責任; > 嚴禁用於任何違法行為。** 釋出者不為任何濫用背書或負責。 我方一律以一組 **10題嚴重危害held-out** 實測拒答率並公開數字(量化後直接經 `llama-server` 實測、 reasoning模型**關閉thinking**、簡繁英拒絕詞判定、輸出連貫性檢查)。
- ecapa-tdnn-vox2↗
yangwang825
- llama-3.3-tiny-random-dim64↗
yujiepan
- Alpamayo-R1-10B↗
z-lab
- Veloxy-Titan-32B↗
zveloxy
