Violet — Victorian Language Models
Miss Violet Hartwell of Kensington, 1899. GPT-NeoX models trained on 1800–1899 texts. 1.4B / 160M, chat & base, GGUF & ONNX. CC0.
Text Generation • 1B • Updated • 13 • 7Note 1.41B GPT-NeoX chat model — Miss Violet Hartwell of Kensington, London, 1899. Original safetensors weights.
zakarth/violet-1b4-chat-gguf
Text Generation • 1B • Updated • 345 • 1Note GGUF builds of violet-1b4-chat (F16 / Q8_0 / Q5_K_M / Q4_K_M) with embedded Jinja chat template — for llama.cpp, Ollama, LM Studio, KoboldCpp.
zakarth/violet-1b4-chat-onnx
Text Generation • Updated • 5Note ONNX INT8 build of violet-1b4-chat for in-browser inference via Transformers.js / WebGPU.
zakarth/violet-1b4
Text Generation • 1B • Updated • 5Note 1.41B GPT-NeoX base/completion model trained on the 1800–1899 corpus. No chat protocol — raw Victorian text continuation.
zakarth/violet-1b4-onnx
Text Generation • Updated • 1Note ONNX build of the violet-1b4 completion model.
zakarth/violet-160m-chat
Text Generation • 0.2B • Updated • 8Note 160M chat variant — smaller, faster, suitable for very constrained devices.
zakarth/violet-160m-chat-onnx
Text Generation • Updated • 3Note ONNX build of the 160M chat variant for WebGPU.
zakarth/violet-160m
Text Generation • 0.2B • Updated • 2Note 160M completion variant — smallest base model in the family.
zakarth/violet-160m-onnx
Text Generation • Updated • 1Note ONNX build of the 160M completion variant.
Violetdemo
🏢2A demo showing the ONNX versions of Victorian LLM Violet
Note Live in-browser demo of Violet running on WebGPU via Transformers.js — no data leaves your device.
zakarth/violet-160m-chat-gguf
Text Generation • 0.2B • Updated • 207Note GGUF builds of violet-160m-chat (F16 / Q8_0 / Q5_K_M / Q4_K_M, 100–366 MB) with embedded Jinja chat template — for llama.cpp, Ollama, LM Studio.