サイト内検索
AI モデル 84757
- CodeFuse-CodeLlama-34B-GGUF↗
TheBloke
- meditron-7B-GGUF↗
TheBloke
- Mistralic-7B-1-GGUF↗
TheBloke
- Seraph-7B-GGUF↗
TheBloke
- Artemis-31B-v1.1↗
TheDrummer
- Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF↗
therickcain
- vit_giantopt_patch16_siglip_384.v2_webli↗
timm
- ViT-SO400M-16-SigLIP-i18n-256↗
timm
- llama3.1-typhoon2-8b-instruct↗
typhoon-ai
**Llama3.1-Typhoon2-8B-instruct** is a instruct Thai 🇹🇭 large language model with 8 billion parameters, and it is based on Llama3.1-8B. For technical-report. please see our arxiv. *To acknowledge Meta's effort in creating the foundation model and to comply with the license, we explicitly include "llama-3.1" in the model name. This model is an instructional model. However, it’s still undergoing development. It incorporates some level of guardrails, but it still may produce answers that are inaccurate, biased, or otherwise objectionable in response to user prompts. We recommend that developers assess these risks in the context of their use case.
- MiniMax-H3-fl2va-ref2va-b25-49-r1024-r0↗
xtanqn
The two official checkpoints are merged into a single **self-contained fused model** that carries both pipelines in one file: The fusion method is **neither training nor LoRA** — it is tensor-level weight fusion. Three headline tiers are provided, ordered by reference-injection strength (`b25-49 → r1024 → r0`; the further right, the stronger the reference capability and the closer to ref2va; the further left, the more fl2va's native orientation is preserved). There are also **AdaLN block-range variants b15 / b20 / b30** (see below; only the starting block differs), ordered along the "preserve fl2va quality + light reference" axis: > All three tiers share the same key layout and quantization format, and can be swapped/loaded at any time. Use `b25-49` for "maximum fl2va quality + a little reference"; use `r1024` for "balanced reference and quality"; use `r0` for "maximum reference, upper-bound comparison".