AIが動く。未来が更新される。clef-flash-GGUF
Cloudflare/clef-flash quantized for llama.cpp. The source is a 9.4B-parameter model (architecture `Qwen3_5ForConditionalGeneration`, 32 layers, hidden size 4096, vocab 248,320), post-trained by Cloudflare from Qwen/Qwen3.5-9B and released under Apache-2.0. This repo has 30 verified files: 29 GGUF quants plus the full-precision BF16 source. Clef-Flash is a **decision model**: it reads a state (text, JSON, images, or video) plus a schema of typed questions and returns a probability for every allowed option of every question in a single forward pass — no free-form text generation, no output parsing. That behavior comes from a backbone plus a separate **joint schema head** (and optionally the vision encoder). For the full decision-model behavior, use Cloudflare/clef-flash directly with `transformers` (5.10.2) and `torch` (2.11) per its README. What you get from this repo in llama.cpp is the post-trained Qwen3.5-9B language tower.
翻訳準備中のため原文を表示しています
Cloudflare/clef-flash quantized for llama.cpp. The source is a 9.4B-parameter model (architecture `Qwen3_5ForConditionalGeneration`, 32 layers, hidden size 4096, vocab 248,320), post-trained by Cloudflare from Qwen/Qwen3.5-9B and released under Apache-2.0. This repo has 30 verified files: 29 GGUF quants plus the full-precision BF16 source. Clef-Flash is a **decision model**: it reads a state (text, JSON, images, or video) plus a schema of typed questions and returns a probability for every allowed option of every question in a single forward pass — no free-form text generation, no output parsing. That behavior comes from a backbone plus a separate **joint schema head** (and optionally the vision encoder). For the full decision-model behavior, use Cloudflare/clef-flash directly with `transformers` (5.10.2) and `torch` (2.11) per its README. What you get from this repo in llama.cpp is the post-trained Qwen3.5-9B language tower.