Instructions to use forkjoin-ai/glm-ocr-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use forkjoin-ai/glm-ocr-gguf 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 forkjoin-ai/glm-ocr-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf forkjoin-ai/glm-ocr-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf forkjoin-ai/glm-ocr-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf forkjoin-ai/glm-ocr-gguf:Q8_0

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 forkjoin-ai/glm-ocr-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf forkjoin-ai/glm-ocr-gguf:Q8_0

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 forkjoin-ai/glm-ocr-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf forkjoin-ai/glm-ocr-gguf:Q8_0

Use Docker

docker model run hf.co/forkjoin-ai/glm-ocr-gguf:Q8_0

LM Studio
Jan

vLLM

How to use forkjoin-ai/glm-ocr-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "forkjoin-ai/glm-ocr-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "forkjoin-ai/glm-ocr-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/forkjoin-ai/glm-ocr-gguf:Q8_0

Ollama
How to use forkjoin-ai/glm-ocr-gguf with Ollama:
```
ollama run hf.co/forkjoin-ai/glm-ocr-gguf:Q8_0
```

Unsloth Studio

How to use forkjoin-ai/glm-ocr-gguf 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 forkjoin-ai/glm-ocr-gguf 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 forkjoin-ai/glm-ocr-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for forkjoin-ai/glm-ocr-gguf to start chatting

Docker Model Runner
How to use forkjoin-ai/glm-ocr-gguf with Docker Model Runner:
```
docker model run hf.co/forkjoin-ai/glm-ocr-gguf:Q8_0
```

Lemonade

How to use forkjoin-ai/glm-ocr-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull forkjoin-ai/glm-ocr-gguf:Q8_0

Run and chat with the model

lemonade run user.glm-ocr-gguf-Q8_0

List all available models

lemonade list

Atomic Chat

buley commited on Mar 20

Commit

827700b

verified ·

1 Parent(s): e9e636d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +24 -45

README.md CHANGED Viewed

@@ -1,74 +1,53 @@
 ---
 language:
   - en
-license: other
-library_name: gguf
 tags:
   - gguf
-  - glm
-  - ocr
-  - document
   - vision
   - affectively
-  - edgework
-  - aether
-  - distributed-inference
-  - edge-deployment
-base_model: THUDM/glm-4v-9b
-base_model_relation: quantized
 pipeline_tag: image-text-to-text
 ---
-# GLM OCR (GGUF, Q4_K_M)
-> **Production-ready** GGUF quantization of [THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) for distributed optical character recognition — powered by the [Aether](https://github.com/affectively-ai/aether) edge inference runtime.
-## Highlights
-- **~2B parameters** — OCR-optimized model based on GLM-4V architecture. Document and scene text recognition.
-- **~2 GB** Q4_K_M quantized — optimized for distributed edge inference
-- **GLM-4 architecture** — proven, stable, well-tested
-- **Aether runtime compatible** — layer-sharded across distributed nodes via [Edgework.ai](https://edgework.ai)
 ## Model Details
-| Property | Value |
-|----------|-------|
-| Base model | [THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) |
-| Parameters | ~2B |
-| Architecture | GLM-4 |
-| Quantization | Q4_K_M |
-| Format | GGUF |
-| Size | ~2 GB |
-| License | other |
 ## Usage
 ### With llama.cpp
 ```bash
-./llama-cli -m glm-ocr-q4_k_m.gguf -p "Your prompt here" -n 256
 ```
-### With Aether (Distributed Inference)
-This model is deployed across the [Aether](https://github.com/affectively-ai/aether) distributed inference network. Weights are layer-sharded and distributed across multiple edge nodes for parallel inference.
-## Deployment Architecture
-This model runs on the **Aether distributed inference runtime** — our custom engine that shards model layers across multiple nodes for parallel execution:
-1. **Coordinator** receives requests and manages token generation
-2. **Layer nodes** each hold a subset of model layers
-3. **Hidden states flow** between nodes via gRPC
-4. **Zero cold start** via warm pool scheduling
-Deployed via [Edgework.ai](https://edgework.ai) — bringing fast, cheap, and private inference as close to the user as possible.
-## About
-Published by [AFFECTIVELY](https://huggingface.co/affectively-ai) · Managed by [@buley](https://huggingface.co/buley)
-We quantize and publish **production-ready models** for distributed edge inference via the [Aether](https://github.com/affectively-ai/aether) runtime. Every release is tested for correctness and stability before publication.
-- [All models](https://huggingface.co/affectively-ai) · [GitHub](https://github.com/affectively-ai) · [Edgework.ai](https://edgework.ai)

 ---
 language:
   - en
+license: apache-2.0
+library_name: llama-cpp
 tags:
   - gguf
   - vision
+  - multimodal
   - affectively
+base_model: THUDM/GLM-OCR
 pipeline_tag: image-text-to-text
 ---
+# Glm Ocr
+AFFECTIVELY conversion of [THUDM/GLM-OCR](https://huggingface.co/THUDM/GLM-OCR) to GGUF format for edge deployment.
 ## Model Details
+- **Source Model**: [THUDM/GLM-OCR](https://huggingface.co/THUDM/GLM-OCR)
+- **Format**: GGUF
+- **Converted by**: [AFFECTIVELY](https://affectively.ai)
 ## Usage
 ### With llama.cpp
 ```bash
+./llama-cli -m glm-ocr-gguf.gguf -p "Your prompt here" -n 256
 ```
+### With Ollama
+Create a `Modelfile`:
+```
+FROM ./glm-ocr-gguf.gguf
+```
+```bash
+ollama create glm-ocr-gguf -f Modelfile
+ollama run glm-ocr-gguf
+```
+## About AFFECTIVELY
+[AFFECTIVELY](https://affectively.ai) is an emotion intelligence platform that runs AI models at the edge -- in-browser, on-device, zero cloud cost. These converted models power the platform's real-time emotion analysis, speech recognition, and natural language capabilities.
+All conversions are optimized for edge deployment within browser and mobile memory constraints.
+## License
+Apache 2.0 (follows upstream model license)