サイト内検索
AI モデル 2119
- Qwen3.8-Flash-Next-131B-A6B-GGUF↗
Cyronius
A 64.8 GB GGUF of Qwen/Qwen3.8-Flash-Next that scores at parity with the full 90 GB quant on tool-calling, GSM8K, and MMLU — 28% smaller, with **zero training and zero transformer surgery**. A 75.4 GB Q4_0 variant of the same cut is also available for older GPUs; see Files. Qwen3.8-Flash-Next carries a 51B-parameter n-gram hash-embedding table (~29% of total weights): 16 independent hash heads, 8 per n-gram type (bigrams / trigrams), injected at layer 1. This model keeps **1 head of 8 per n-gram type** and drops the other 14, exploiting the built-in redundancy of multi-head hashing (each n-gram is looked up several independent ways; a Bloom-filter-style safety margin). Every other tensor is copied **byte-for-byte** from unsloth's UD-Q3_K_XL dynamic quant, so unsloth's imatrix calibration is preserved exactly. The Q4_0 build is **bigger**, not smaller. The n-gram table is what makes this model compact; Q4_0 simply stores every other tensor at more bits than Q3_K_XL does. You are buying throughput with VRAM. On gfx906 that trade is usually worth it — Q4_0 reaches llama.cpp's MMVQ path while K-quants and IQ4_NL fall through to a generic dequant path several times slower.
- llama-3-70B-Instruct-abliterated↗
failspy
This is meta-llama/Llama-3-70B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more. TL;DR: this model has had certain weights manipulated to "inhibit" the model's ability to express refusal. It is not in anyway _guaranteed_ that it won't refuse you, understand your request, it may still lecture you about ethics/safety, etc. It is tuned in all other respects the same as the original 70B instruct model was, just with the strongest refusal direction orthogonalized out. In the repo, I've included `refusal_dir.pth` If you have Llama-3-70B-Instruct model downloaded already, you can use the ortho cookbook to apply it to your downloaded model, which will make it the same as what you'd download from here.
- Florence-2-base↗
florence-community
> [!NOTE] > This is the repository for official transformers converted checkpoint of Microsoft's Florence model. **This is a continued pretrained version of Florence-2-large model with 4k context length, only 0.1B samples are used for continue pretraining, thus it might not be trained well. In addition, OCR task has been updated with line separator ('\n'). COCO OD AP 39.8** Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages our FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model's sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model.
- wav2vec2-large-xlsr-53-spanish↗
jonatasgrosman
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Spanish using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
- LFM2.5-24B-A2B-APEX-GGUF↗
mudler
Perplexity is measured on wikitext-2-raw. KL divergence is measured against the BF16 model on the same text. HellaSwag and Winogrande use 400 tasks each, zero-shot. The LiquidAI rows are the quantizations published by LiquidAI, measured the same way. Perplexity differences of about 0.2 are close to the measurement error (+/- 0.14). APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient: edge layers get higher precision, middle layers get more aggressive compression. The I-variants use imatrix-guided quantization. APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.
- awm-minimax-h3-new1344-lora-checkpoints↗
NTU-yiwen
This repository publicly releases five selected CWM LoRA adapters from our MiniMax-H3 1344×768 q4 System-Chat training runs. The repository contains five adapters totaling 11,927,917,704 bytes. Each adapter contains 600 LoRA tensors for 200 target modules. The official MiniMax-H3 Ref2VA base model is not included. These checkpoints support inference and LoRA weight warm-start with the matching MiniMax-H3 Ref2VA base model. They do not support optimizer-level exact training resumption because optimizer, scheduler, dataloader, sampler, and RNG states are not included.
- lfm2.5-2.6b-fable5-coding-agent-heretic↗
saidutta69
A decensored variant of AyoubChLin/lfm2.5-2.6b-fable5-coding-agent (full-parameter SFT of LiquidAI/LFM2.5-2.6B on saidutta69/fable-5-premium), produced with Heretic v1.4.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's coding-agent capabilities, tool-use patterns, and instruction-following are left largely intact. **Who this is for:** developers who want a compact 2.6B coding agent with LFM2's hybrid conv+attention architecture — fast inference, tool-call generation, code generation, and multi-turn assistant behavior — without refusal guardrails. Not a capability upgrade over the base model — same model, refusal guardrails removed. Weights only, at this model's 2.7B native size; add ~1 GB for context. OOM? Drop one quant level. Headroom to spare? Go one up.
- all-MiniLM-L6-v1↗
sentence-transformers
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained `nreimers/MiniLM-L6-H384-uncased` model and fine-tuned in on a 1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
- LTX-Video-0.9.6-distilled-gguf↗
city96
The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders: The VAE seems to be largely the same as LTXV 0.9.5 and the difference between the two seems negligible, but I've uploaded the 0.9.6 one to this repo to be safe *As this is a quantized model not a finetune, all the same restrictions/original license terms still apply.*
- bert_uncased_L-4_H-512_A-8↗
Google
This is the set of 24 BERT models referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (English only, uncased, trained with WordPiece masking). We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher. Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.