Instructions to use HOLOGRAMTECH/q-olmoe-1b-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HOLOGRAMTECH/q-olmoe-1b-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HOLOGRAMTECH/q-olmoe-1b-7b",
	filename="tokenizer.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use HOLOGRAMTECH/q-olmoe-1b-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 HOLOGRAMTECH/q-olmoe-1b-7b
# Run inference directly in the terminal:
llama cli -hf HOLOGRAMTECH/q-olmoe-1b-7b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HOLOGRAMTECH/q-olmoe-1b-7b
# Run inference directly in the terminal:
llama cli -hf HOLOGRAMTECH/q-olmoe-1b-7b

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf HOLOGRAMTECH/q-olmoe-1b-7b
# Run inference directly in the terminal:
./llama-cli -hf HOLOGRAMTECH/q-olmoe-1b-7b

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf HOLOGRAMTECH/q-olmoe-1b-7b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HOLOGRAMTECH/q-olmoe-1b-7b

Use Docker

docker model run hf.co/HOLOGRAMTECH/q-olmoe-1b-7b

LM Studio
Jan

vLLM

How to use HOLOGRAMTECH/q-olmoe-1b-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HOLOGRAMTECH/q-olmoe-1b-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HOLOGRAMTECH/q-olmoe-1b-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HOLOGRAMTECH/q-olmoe-1b-7b

Ollama
How to use HOLOGRAMTECH/q-olmoe-1b-7b with Ollama:
```
ollama run hf.co/HOLOGRAMTECH/q-olmoe-1b-7b
```

Unsloth Studio

How to use HOLOGRAMTECH/q-olmoe-1b-7b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HOLOGRAMTECH/q-olmoe-1b-7b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HOLOGRAMTECH/q-olmoe-1b-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HOLOGRAMTECH/q-olmoe-1b-7b to start chatting

Atomic Chat new
Docker Model Runner
How to use HOLOGRAMTECH/q-olmoe-1b-7b with Docker Model Runner:
```
docker model run hf.co/HOLOGRAMTECH/q-olmoe-1b-7b
```

Lemonade

How to use HOLOGRAMTECH/q-olmoe-1b-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HOLOGRAMTECH/q-olmoe-1b-7b

Run and chat with the model

lemonade run user.q-olmoe-1b-7b-{{QUANT_TAG}}

List all available models

lemonade list

Humuhumu33 commited on 13 days ago

Commit

eca2bfd

verified ·

1 Parent(s): cb5ac87

Add branded Hologram model card

Browse files

Files changed (1) hide show

README.md +84 -0

README.md ADDED Viewed

	@@ -0,0 +1,84 @@

+---
+license: apache-2.0
+base_model: allenai/OLMoE-1B-7B-0924-Instruct
+pipeline_tag: text-generation
+inference: false
+tags:
+- hologram
+- q
+- kappa-object
+- holo
+- moe
+- olmoe
+- allenai
+---
+<div align="center">
+# Hologram · OLMoE-1B-7B
+**Mixture of experts (64 x 8)**
+`q4 · MoE` · `3.6 GB` · streamed to Q as a **key-addressable `.holo` object**
+[Hologram](https://gethologram.ai) · [Live Space](https://huggingface.co/spaces/HOLOGRAMTECH/hologram) · [Organization](https://huggingface.co/HOLOGRAMTECH) · [Code](https://github.com/Hologram-Technologies)
+</div>
+---
+## What this is
+The first resident-MoE key object: 64 experts held in memory with an 8-of-64 top-k router. About 1.3B active parameters of a 7B model per token.
+This repository is **not** a GGUF or Transformers checkpoint. It is a **Hologram key object**: the weights of `allenai/OLMoE-1B-7B-0924-Instruct` re-encoded into Hologram's content-addressed `.holo` format so they stream, one verified block at a time, into **Q**, the on-device brain of the Hologram web OS. It runs in the browser on WebGPU, serverless, with nothing to install.
+## How it streams
+The object is laid out for cold streaming from an untrusted CDN:
+| File | Role |
+|---|---|
+| `manifest.json` | the root. Names every tensor and the key (content hash) of its block. |
+| `b/sha256_*.gz` | the tensor blocks. Each filename **is** the SHA-256 of its bytes. |
+| `tokenizer.gguf` | bundled header (where present), so loading is fully serverless. |
+Q fetches the manifest, then pulls each block by its key and re-derives `sha256(block)` on arrival. If a byte is wrong, the block is rejected. Nothing is trusted; everything is proven.
+## Verify (Law L5)
+The object's identity is the SHA-256 of its manifest, pinned in Q's catalog before a single byte of weight is trusted:
+```
+did:holo:sha256:9cf97ec1c761fd4ef51bc0cd4ac37a0cd8eaa11f1b19b3ae6a141486ad3fe5ad
+```
+```bash
+# the manifest hash equals the pinned identity above
+curl -sL https://huggingface.co/HOLOGRAMTECH/q-olmoe-1b-7b/resolve/main/manifest.json   | sha256sum
+```
+## Specifications
+| | |
+|---|---|
+| Architecture | OLMoE (64 experts, 8 active) |
+| Precision | q4 · MoE |
+| Object size | 3.6 GB |
+| Hidden size | 2048 |
+| Layers | 16 |
+| Heads (Q / KV) | 16 / 16 |
+| FFN | 1024 x 64 experts |
+| Vocab | 50304 |
+| Context | 3000 |
+| Format | `holo-2bit/1` |
+## Provenance and license
+Derived from [`allenai/OLMoE-1B-7B-0924-Instruct`](https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct).  The re-encoding is lossless-by-construction at the key level: every block is content-addressed, so the object either re-derives to its pinned identity or it is refused.
+## Run it
+These weights load through Q, not a standard runtime. Open the [Live Space](https://huggingface.co/spaces/HOLOGRAMTECH/hologram) or visit [gethologram.ai](https://gethologram.ai) to run Hologram, then pick **OLMoE-1B-7B** from Q's model list.
+<div align="center"><sub>Composed on the golden ratio. One key, everything.</sub></div>