Search FoxAI
AI Models 84767
- SentimentArEng↗
qandos0
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.502831 - Accuracy: 0.798512 - The following hyperparameters were used during training: - learning_rate=2e-5 - num_train_epochs=20 - weight_decay=0.01 - batch_size=16, - Transformers 4.35.0 - Pytorch 2.0.0 - Datasets 2.11.0 - Tokenizers 0.14.1
- gemma-4-31B-it-NVFP4↗
RedHatAI
- **Model Architecture:** Gemma4ForConditionalGeneration - **Input:** Text / Image - **Output:** Text - **Model Optimizations:** - **Weight quantization:** FP4 - **Activation quantization:** FP4 - **Release Date:** 2026-04-04 - **Version:** 1.0 - **Model Developers:** RedHatAI This model is a quantized version of google/gemma-4-31B-it. It was evaluated on several tasks to assess its quality in comparison to the unquantized model. This model was obtained by quantizing the weights and activations of google/gemma-4-31B-it to FP4 data type using the NVFP4 format, ready for inference with vLLM. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
- rwkv7-g1h-7.2b-GGUF↗
RemySkye
- Bina-0.1-Koochik↗
Reza2kn
- ambrosfitz_-_TinyLlama-1.1B-Chat-yawp-gguf↗
RichardErkhov
- CallComply_-_SOLAR-10.7B-Instruct-v1.0-128k-gguf↗
RichardErkhov
- CorticalStack_-_neurotic-crown-clown-7b-ties-gguf↗
RichardErkhov
- failspy_-_Phi-3-mini-128k-instruct-abliterated-v3-gguf↗
RichardErkhov
- Smashitup_-_FineLlama-3.1-8B-q3_k_m-GGUF-gguf↗
RichardErkhov
- Qwen3-14B-abliterated-GGUF↗
richardyoung
An **abliterated** (uncensored) version of Qwen/Qwen3-14B in GGUF format for local inference. Conservative abliteration preserves model coherence while significantly reducing refusals. Abliteration removes the "refusal direction" from a model's residual stream — a surgical modification that disables safety refusals without retraining. See Refusal in Language Models Is Mediated by a Single Direction.
