Downloads · 30 days
143
8% of all-time downloads
srs6901/GGUF-SOLARized-GraniStral-14B_1902_YeAM-HCT
GGUF-SOLARized-GraniStral-14B_1902_YeAM-HCT is a text generation model from srs6901. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This repository contains GGUF-only artifacts for convenience (search / indexing / quick downloads).
Downloads · 30 days
143
8% of all-time downloads
All-time downloads
1.8K
Public
Repo size
35.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf35.4 GB · 100%
From the Hugging Face model README
This repository contains GGUF-only artifacts for convenience (search / indexing / quick downloads).
If you need the original weights, tokenizer files, chat templates, or anything beyond GGUF inference — use the main repo above.
| Quant | File | Link |
|---|---|---|
| Q4_K | SOLARized-GraniStral-14B_1902_YeAM-HCT_Q4.gguf | download |
| Q5_K | SOLARized-GraniStral-14B_1902_YeAM-HCT_Q6.gguf | download |
| Q6_K | SOLARized-GraniStral-14B_1902_YeAM-HCT_Q8.gguf | download |
| FP32 | mmproj-SOLARized-GraniStral-14B_1902_YeAM-HCT_F32.gguf | download |
Это репозиторий только с GGUF для удобства поиска/индексации и быстрого скачивания.
SOLARized-GraniStral-14B_1902_YeAM-HCT — экспериментальный beta-мердж на базе Ministral-3-14B-Instruct-2512 (text+vision) с примесью SOLAR и IBM Granite.
*.gguf: готовые GGUF-кванты для llama.cpp/совместимых рантаймов.[/INST], это обычно проблема метаданных токенизатора (pretok/token types) — см. заметки в основном репозитории модели.llama.cpp обычно нужен GGUF модели плюс отдельный mmproj GGUF (projector) — см. основной репозиторий.Важно: мультимодальность llama.cpp для Pixtral/Mistral3 сейчас активно меняется; качество понимания изображений может быть некорректным даже если HF/Transformers работает правильно.
This is a GGUF-only repository for convenience (search / indexing / quick downloads).
SOLARized-GraniStral-14B_1902_YeAM-HCT is an experimental beta merge built on top of Ministral-3-14B-Instruct-2512 (text+vision), with donor influence from SOLAR and IBM Granite.
*.gguf: ready-to-use GGUF quants for llama.cpp and compatible runtimes.[/INST] in output, it is almost always a tokenizer metadata issue (token types / pretok). See the main repo for the exact intended configuration.llama.cpp, expect a model GGUF plus a separate mmproj GGUF (projector). See the main repo.Important: llama.cpp multimodal support for Pixtral/Mistral3 is under heavy development. In practice, image understanding quality may be incorrect even when HF/Transformers works correctly.
Apache-2.0. Base model licenses apply for the corresponding upstream artifacts.