Nanite-Labs/ medieval

2 Downloads Updated 6 days ago

tools thinking

ollama run Nanite-Labs/medieval:q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Nanite-Labs/medieval:q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Nanite-Labs/medieval:q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Nanite-Labs/medieval:q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model Nanite-Labs/medieval:q4_k_m

OpenCode

OpenCode ollama launch opencode --model Nanite-Labs/medieval:q4_k_m

Hermes Agent

Hermes Agent ollama launch hermes --model Nanite-Labs/medieval:q4_k_m

OpenClaw

OpenClaw ollama launch openclaw --model Nanite-Labs/medieval:q4_k_m

Models

Name

1 model

Size / Usage

Context

Input

medieval:q4_k_m

3.4GB · 128K context window · Text · 6 days ago

medieval:q4_k_m

3.4GB

128K

Text

Readme

medieval

Q4_K_M quant of the merged nanites-medieval-e2b-chat model — a Gemma-4-E2B fine-tune that speaks as a literate person of late-medieval England, a 15th-century letter-writer drawn from real pre-1500 letters and papers.

ollama run Nanite-Labs/medieval:q4_k_m "How fares your household this season?"

Requires a recent Ollama (Gemma 4 support).

What it does

Ask it like a visitor asking a 1400s gentleman about the harvest, the wool market, a lawsuit, the war in France, or a daughter’s marriage. 1–3 sentences with period vocabulary (“thou”, “hath”, “good cousin”) — modernized, never verbatim Middle English. Multi-turn works.

What it doesn’t do

No fact-check layer. Names, dates, places, legal details are creative writing in a historical register, not history. Not for settling real historical questions.

Training

Base: Gemma-4-E2B (text tower only) · Method: QLoRA r=16 · Data: 50 hand-authored seed Q&A + ~200 distilled pairs grounded in pre-1500 letters and verse (CEECS sample, Paston Letters, Chaucer, Gower, Langland, Lydgate, Hoccleve; corpus reproducible, not redistributed) + multi-turn conversations.

Provenance & license

Adapter + recipe: Apache 2.0 (Nanites Laboratories). Base model: Gemma Terms of Use.
Full weights + LoRA adapter: https://huggingface.co/Nanite-Labs/nanites-medieval-e2b-chat · GGUF: https://huggingface.co/Nanite-Labs/nanites-medieval-e2b-chat-gguf

# medieval

Q4_K_M quant of the merged **nanites-medieval-e2b-chat** model — a Gemma-4-E2B fine-tune that speaks as a literate person of late-medieval England, a 15th-century letter-writer drawn from real pre-1500 letters and papers.

```bash
ollama run Nanite-Labs/medieval:q4_k_m "How fares your household this season?"
```

Requires a recent Ollama (Gemma 4 support).

## What it does

Ask it like a visitor asking a 1400s gentleman about the harvest, the wool market, a lawsuit, the war in France, or a daughter's marriage. 1–3 sentences with period vocabulary ("thou", "hath", "good cousin") — modernized, never verbatim Middle English. Multi-turn works.

## What it doesn't do

- No fact-check layer. Names, dates, places, legal details are creative writing in a historical register, not history. Not for settling real historical questions.

## Training

- Base: Gemma-4-E2B (text tower only) · Method: QLoRA r=16 · Data: 50 hand-authored seed Q&A + ~200 distilled pairs grounded in pre-1500 letters and verse (CEECS sample, Paston Letters, Chaucer, Gower, Langland, Lydgate, Hoccleve; corpus reproducible, not redistributed) + multi-turn conversations.

## Provenance & license

- Adapter + recipe: Apache 2.0 (Nanites Laboratories). Base model: Gemma Terms of Use.
- Full weights + LoRA adapter: https://huggingface.co/Nanite-Labs/nanites-medieval-e2b-chat · GGUF: https://huggingface.co/Nanite-Labs/nanites-medieval-e2b-chat-gguf

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)