Instructions to use Notacape/EdgeDecoder-JAX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Notacape/EdgeDecoder-JAX 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 Notacape/EdgeDecoder-JAX:F16
# Run inference directly in the terminal:
llama cli -hf Notacape/EdgeDecoder-JAX:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Notacape/EdgeDecoder-JAX:F16
# Run inference directly in the terminal:
llama cli -hf Notacape/EdgeDecoder-JAX:F16

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 Notacape/EdgeDecoder-JAX:F16
# Run inference directly in the terminal:
./llama-cli -hf Notacape/EdgeDecoder-JAX:F16

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 Notacape/EdgeDecoder-JAX:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Notacape/EdgeDecoder-JAX:F16

Use Docker

docker model run hf.co/Notacape/EdgeDecoder-JAX:F16

LM Studio
Jan

vLLM

How to use Notacape/EdgeDecoder-JAX with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Notacape/EdgeDecoder-JAX:F16

Ollama
How to use Notacape/EdgeDecoder-JAX with Ollama:
```
ollama run hf.co/Notacape/EdgeDecoder-JAX:F16
```
Unsloth Desktop
Docker Model Runner
How to use Notacape/EdgeDecoder-JAX with Docker Model Runner:
```
docker model run hf.co/Notacape/EdgeDecoder-JAX:F16
```

Lemonade

How to use Notacape/EdgeDecoder-JAX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Notacape/EdgeDecoder-JAX:F16

Run and chat with the model

lemonade run user.EdgeDecoder-JAX-F16

List all available models

lemonade list

Atomic Chat

EdgeDecoder-JAX / config.json

Notacape

MicroGPT-2 SFT: safetensors (Qwen3 layout) + GGUF f16 and q8_0

1769200 verified 6 days ago

Raw

History Blame Contribute Delete

642 Bytes

	{
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"model_type": "qwen3",
	"vocab_size": 49152,
	"hidden_size": 1280,
	"intermediate_size": 3328,
	"num_hidden_layers": 25,
	"num_attention_heads": 10,
	"num_key_value_heads": 5,
	"head_dim": 128,
	"hidden_act": "silu",
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000.0,
	"rope_scaling": null,
	"max_position_embeddings": 1024,
	"tie_word_embeddings": true,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"use_cache": true,
	"sliding_window": null,
	"use_sliding_window": false,
	"torch_dtype": "float32",
	"bos_token_id": 0,
	"eos_token_id": 2,
	"pad_token_id": 0
	}