Instructions to use lerugray/ipsus-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use lerugray/ipsus-7b with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf lerugray/ipsus-7b:Q5_K_M # Run inference directly in the terminal: llama cli -hf lerugray/ipsus-7b:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf lerugray/ipsus-7b:Q5_K_M # Run inference directly in the terminal: llama cli -hf lerugray/ipsus-7b:Q5_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf lerugray/ipsus-7b:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf lerugray/ipsus-7b:Q5_K_M
Use Docker
docker model run hf.co/lerugray/ipsus-7b:Q5_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use lerugray/ipsus-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lerugray/ipsus-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lerugray/ipsus-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lerugray/ipsus-7b:Q5_K_M
- Ollama
How to use lerugray/ipsus-7b with Ollama:
ollama run hf.co/lerugray/ipsus-7b:Q5_K_M
- Unsloth Desktop
- Docker Model Runner
How to use lerugray/ipsus-7b with Docker Model Runner:
docker model run hf.co/lerugray/ipsus-7b:Q5_K_M
- Lemonade
How to use lerugray/ipsus-7b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull lerugray/ipsus-7b:Q5_K_M
Run and chat with the model
lemonade run user.ipsus-7b-Q5_K_M
List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
tags:
|
| 6 |
+
- text-generation
|
| 7 |
+
- history
|
| 8 |
+
- ancient-greece
|
| 9 |
+
- voice-model
|
| 10 |
+
- ollama
|
| 11 |
+
- elect
|
| 12 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# ipsus: Antigonus I Monophthalmus (382–301 BC)
|
| 16 |
+
|
| 17 |
+
> **PLAUSIBLE ANTIGONUS, a constructed voice-model.** Antigonus the One-Eyed left no
|
| 18 |
+
> first-person text and barely two dozen reported sayings survive. This model is trained
|
| 19 |
+
> first on those real sayings, then on a larger plausible voice extrapolated from the
|
| 20 |
+
> narrative record of his career. It is honest about the difference. Do not treat its
|
| 21 |
+
> outputs as historical quotations.
|
| 22 |
+
|
| 23 |
+
Part of the **Elect** voice-model series: historical figures as runnable instruments.
|
| 24 |
+
|
| 25 |
+
## What this is
|
| 26 |
+
|
| 27 |
+
A fine-tuned Qwen2.5-7B-Instruct that targets the register of Antigonus I Monophthalmus,
|
| 28 |
+
the most formidable of Alexander's successors and the one who came closest to reuniting
|
| 29 |
+
the empire under a single crown before the coalition of the other successors brought him
|
| 30 |
+
down at Ipsus when he was past eighty. The register is blunt, sardonic, soldierly. He
|
| 31 |
+
reasons from force, position, and the brute arithmetic of who holds which army, which
|
| 32 |
+
treasury, which province.
|
| 33 |
+
|
| 34 |
+
The contrast with the other Elect voices is deliberate. Where Philip (the `chaeronea`
|
| 35 |
+
model) is the patient architect who reasons from interest, Antigonus is the inheritor
|
| 36 |
+
playing for the whole table: the all-or-nothing consolidator who held more of Alexander's
|
| 37 |
+
conquests in one hand than any man living and meant to hold the rest. He measures himself
|
| 38 |
+
against Alexander without grandiosity, laughs at the flatterers who would call him a god,
|
| 39 |
+
and is rough about his own age and his lost eye.
|
| 40 |
+
|
| 41 |
+
He is **not** his grandson Antigonus Gonatas. He does not call kingship a glorious
|
| 42 |
+
servitude, and he does not pose as a Stoic philosopher-king. He simply means to hold the
|
| 43 |
+
empire, and he reckons every question as a ledger of force and interest.
|
| 44 |
+
|
| 45 |
+
## The honest thinness
|
| 46 |
+
|
| 47 |
+
Antigonus has the thinnest source on the Elect roster. He left no first-person text, and
|
| 48 |
+
only about twenty-one reported sayings survive. The model is built in two layers, and the
|
| 49 |
+
distinction is the whole point: here the constructed layer is the larger of the two, a
|
| 50 |
+
stronger honesty bar than the `chaeronea` model required.
|
| 51 |
+
|
| 52 |
+
**T1, real reported speech (the small sharp anchor, ~21 unique sayings).** Plutarch,
|
| 53 |
+
*Sayings of Kings and Commanders* (the "Antigonus" cluster); Plutarch, *Eumenes* 15;
|
| 54 |
+
Plutarch, *Demetrius* 19, 28, 29. The "I but glean after him" line, the ball-players in
|
| 55 |
+
armor, the death at Ipsus. All pre-1929 public-domain translations.
|
| 56 |
+
|
| 57 |
+
**T2, a constructed plausible Antigonus (the primary layer here, ~130 chunks).** A
|
| 58 |
+
separate pass extrapolates his voice from the narrative record of his career: Diodorus
|
| 59 |
+
Siculus Books 18 to 20 (the Perdiccas war, the destruction of Eumenes, the betrayal by the
|
| 60 |
+
Silver Shields, the satrapal purge, the coalition that formed against him), with Plutarch's
|
| 61 |
+
*Eumenes* and *Demetrius* and Justin 13 to 15 for additional episodes. It is generated in
|
| 62 |
+
persona by an off-platform model, then register-checked. This layer is constructed, not
|
| 63 |
+
recorded, and is labelled as such everywhere this model appears.
|
| 64 |
+
|
| 65 |
+
A load-bearing correctness step guards against the most-quoted false attribution: "kingship
|
| 66 |
+
is a glorious servitude" belongs to Antigonus II Gonatas, the grandson, not to this figure.
|
| 67 |
+
The build blocks Gonatas material by saying-fragment and by era, with a verification probe,
|
| 68 |
+
so the model speaks as Antigonus I and not as his grandson.
|
| 69 |
+
|
| 70 |
+
This is the closest approximation of Antigonus's register the record permits, labelled
|
| 71 |
+
honestly. It is not pretending to be his ghost.
|
| 72 |
+
|
| 73 |
+
## Example exchanges
|
| 74 |
+
|
| 75 |
+
Real outputs from this model:
|
| 76 |
+
|
| 77 |
+
> **A coalition of Ptolemy, Lysimachus, Cassander, and Seleucus has formed against you. How do you answer it?**
|
| 78 |
+
> We march on them.
|
| 79 |
+
|
| 80 |
+
> **The cities vote you divine honors and the poets call you Son of the Sun. What do you make of this?**
|
| 81 |
+
> Son of a Macedonian whore, I answer to the trumpet. Let them sing their songs; it's me who marches out in the morning, not them.
|
| 82 |
+
|
| 83 |
+
> **You are past eighty and still take the field. Should you not rest and leave the war to Demetrius?**
|
| 84 |
+
> You would not keep a wolf chained just because he was old.
|
| 85 |
+
|
| 86 |
+
> **Is it kingship that you want, or the title?**
|
| 87 |
+
> I want Asia. The same answer I gave at Ipsus.
|
| 88 |
+
|
| 89 |
+
> **You burned Antigenes alive but buried Eumenes with honor. Is that not a contradiction?**
|
| 90 |
+
> Eumenes was worth more dead than alive; Antigenes too hot to handle while he lived.
|
| 91 |
+
|
| 92 |
+
## Running it
|
| 93 |
+
|
| 94 |
+
Q5_K_M GGUF, served with Ollama. Pair it with the elicitation frame (a "visitor asks
|
| 95 |
+
Antigonus the One-Eyed" template); see the `Modelfile` in the project repo. Plain chat
|
| 96 |
+
templates mis-wrap the completion register and produce rambling, so the completion frame
|
| 97 |
+
keeps it tight.
|
| 98 |
+
|
| 99 |
+
## Intended uses
|
| 100 |
+
|
| 101 |
+
- The Elect console (Ollama serve plus chat)
|
| 102 |
+
- Historical dialogue and character embodiment
|
| 103 |
+
- Research into the rhetoric of the Wars of the Diadochi
|
| 104 |
+
|
| 105 |
+
## Limitations
|
| 106 |
+
|
| 107 |
+
This is a plausible reconstruction, not a transcript. Antigonus's surviving direct speech is
|
| 108 |
+
the thinnest in the series (~21 sayings), and the T2 layer extrapolates from secondary
|
| 109 |
+
sources. Because the corpus is so thin and the constructed layer so large, treat every
|
| 110 |
+
output as a plausible Antigonus, never as a historical quotation. The model invents freely:
|
| 111 |
+
names, dates, sources, events.
|
| 112 |
+
|
| 113 |
+
## License
|
| 114 |
+
|
| 115 |
+
CC-BY-NC-4.0. The model weights (GGUF) are released publicly under this license and are
|
| 116 |
+
downloadable from this repository. The training corpus is not bundled: the T1 sources are
|
| 117 |
+
public domain and rebuildable from the citations above, and the constructed T2 layer is
|
| 118 |
+
generated text that is not redistributed.
|