Search FoxAI
AI Models 84768
- Qwen2.5-7B-Instruct-Uncensored-GGUF↗
QuantFactory
license: gpl-3.0 datasets: - NobodyExistsOnTheInternet/ToxicQAFinal - anthracite-org/kalo-opus-instruct-22k-no-refusal - Orion-zhen/dpo-toxic-zh - unalignment/toxic-dpo-v0.2 - Crystalcareai/Intel-DPO-Pairs-Norefusals language: - zh - en base_model: - Qwen/Qwen2.5-7B-Instruct pipeline_tag: text-generation tags: - qwen - uncensored This model is an uncensored fine-tune version of Qwen2.5-7B-Instruct. However, I can still notice that though uncensored, the model fails to generate detailed descriptions on certain extreme scenarios, which might be associated with deletion on some pretrain datasets in Qwen's pretraining stage. Check out my roleplay&writing enhanced model based on this model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
- granite-embedding-english-r2↗
RedHatAI
- STEM-AI-mtl_-_phi-2-electrical-engineering-gguf↗
RichardErkhov
- Qwen3-1.7B-Q4_K_M-GGUF↗
rippertnt
- rf-detr-nano↗
Roboflow
- gemma-4-E4B-it-heretic-QAT-GGUF↗
SC117
Uncensored version of Google Gemma 4 E4B IT (QAT) , processed with Heretic ARA abliteration. Quantized to Q4_0 — only 4 GB, perfect for mobile and edge devices . start_layer_index 20 end_layer_index 36 preserve_good_behavior_weight 0.5805 steer_bad_behavior_weight 0.0023 overcorrect_relative_weight 0.7764 neighbor_count 13 Base Model google/gemma-4-E4B-it Parameters 4.5B effective (8B with PLE embeddings) Architecture Dense with Per-Layer Embeddings (PLE) + multimodal Layers 42 Hidden Size 2,560 Context Length 128K tokens Vocabulary 262K, 140+ languages Modalities Text + Image + Audio + Video Quantization Q4_0 (matching Unsloth UD-Q4_K_XL layout), b9553 llama-quantize
- OmniVoice-GGUF↗
Serveurperso
GGUF weights for omnivoice.cpp, a C++17/GGML port of OmniVoice (k2-fsa/OmniVoice). Multilingual zero shot TTS, 646 languages, 24 kHz mono. Runs on CPU, CUDA, ROCm, Metal, Vulkan. omnivoice-base-{variant}.gguf Qwen3 0.6B backbone, text -> tokens omnivoice-tokenizer-{variant}.gguf HuBERT + DAC + RVQ, tokens 24 kHz audio Set `GGML_BACKEND` to force a device, otherwise the runtime picks the best one available.
- Index-Translate-9B-IQ4_XS-GGUF↗
shoutmon
- Qwen3.6-35B-DFlash-GGUF↗
starskyzheng
- starvector-8b-im2svg↗
starvector
