全站搜索
AI 模型 85004
- Udgam-384M-Base-4K↗
udgamlabs
- Phi-3-medium-4k-instruct↗
unsloth
- VecGlypher-27b-it-Q4_K_M-GGUF↗
wahidmounir
- kana-whisper↗
0x3
- WizardLM-13B-Uncensored-4bit-128g↗
4bit
- GPT-NeoX-1.3B-viet-final-GGUF↗
afrideva
- qwen2-57b-a14b-instruct↗
阿里巴巴 · Qwen
Qwen2 是 Qwen 大型语言模型的新系列。针对 Qwen2,我们发布了参数量从 0.5 亿到 720 亿不等的多个基础语言模型和指令微调语言模型,其中包括混合专家模型。本仓库包含经过指令微调的 57B-A14B 混合专家 Qwen2 模型。与最先进的开源语言模型(包括此前发布的 Qwen1.5)相比,Qwen2 在面向语言理解、语言生成、多语言能力、编码、数学、推理等一系列基准测试中,整体上已超越大多数开源模型,并展现出媲美专有模型的竞争力。Qwen2-57B-A14B-Instruct 支持长达 65,536 个 token 的上下文长度,能够处理超长输入。有关如何部署 Qwen2 处理长文本的详细说明,请参阅本节。
- Hemmingway-1-Unlocked-GGUF↗
amylynn
- LFM2.5-2.6B-GGUF-shards↗
Arki05
- `source/`: LiquidAI's BF16 GGUF (LiquidAI/LFM2.5-2.6B-GGUF), unchanged. - `types/ -hq.gguf`, `types/ -hq1.gguf`: the tensors at llama.cpp type `T`, rebuilt from the BF16 weights in two Hessian-quantized (GPTQ-family) builds: `-hq`, the higher-quality one, the block tensors; `-hq1`, the first build, every quantized tensor. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `data/`: the calibration data the types were made from (token ids and their manifest). - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The first version of this store (bartowski's BF16 GGUF and imatrix, types by llama.cpp's `llama-quantize`) is at revision `fe50613`.
- Art-v0-3B-GGUF↗
bartowski
