Downloads · 30 days
31
26% of all-time downloads
Vertex-0.6-15M-Base-GGUF
VertexResearch/Vertex-0.6-15M-Base-GGUF
Vertex-0.6-15M-Base-GGUF is a text generation model from VertexResearch. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Base (pretrain-only) checkpoint of Vertex 0.6 15M, a tiny ~15M-param model from the Vertex 0.6 family. Qwen3 architecture: hidden 256, 10 layers, 4 heads / 2 KV (GQA, headdim 64), SwiGLU ffn 1024, 20000-vocab ByteLeve…
All-time downloads
118
Public
Repo size
30.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf30.6 MB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- b05bf919
Try a prompt
Base models
Model card
From the Hugging Face model README
Vertex 0.6 15M Base
Base (pretrain-only) checkpoint of Vertex 0.6 15M, a tiny ~15M-param model from the Vertex 0.6 family. Qwen3 architecture: hidden 256, 10 layers, 4 heads / 2 KV (GQA, head_dim 64), SwiGLU ffn 1024, 20000-vocab ByteLevel BPE, tied embeddings, ctx 2048.
Pretrained from scratch on 12B tokens of English web text: Ultra-FineWeb plus Ultra-FineWeb-L3 synthetic rewrites (Multi-Style + QA), ~800 tokens per parameter, on a single RTX 4060 Laptop (8GB).
This is a raw language model — no chat template, no instruction tuning. For chat, see Vertex-0.6-15M-Instruct.
Training data
Pretrained on English web text from openbmb/Ultra-FineWeb and openbmb/Ultra-FineWeb-L3 (Multi-Style + QA synthetic configs), 12B tokens total.
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026