Instructions to use Subject-Emu-5259/NeuralAI-Mamba-K1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Subject-Emu-5259/NeuralAI-Mamba-K1 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 Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

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 Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

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 Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

Use Docker

docker model run hf.co/Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

LM Studio
Jan

vLLM

How to use Subject-Emu-5259/NeuralAI-Mamba-K1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Subject-Emu-5259/NeuralAI-Mamba-K1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Subject-Emu-5259/NeuralAI-Mamba-K1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

Ollama
How to use Subject-Emu-5259/NeuralAI-Mamba-K1 with Ollama:
```
ollama run hf.co/Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
```

Unsloth Studio

How to use Subject-Emu-5259/NeuralAI-Mamba-K1 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 Subject-Emu-5259/NeuralAI-Mamba-K1 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 Subject-Emu-5259/NeuralAI-Mamba-K1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Subject-Emu-5259/NeuralAI-Mamba-K1 to start chatting

Docker Model Runner
How to use Subject-Emu-5259/NeuralAI-Mamba-K1 with Docker Model Runner:
```
docker model run hf.co/Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M
```

Lemonade

How to use Subject-Emu-5259/NeuralAI-Mamba-K1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Subject-Emu-5259/NeuralAI-Mamba-K1:Q4_K_M

Run and chat with the model

lemonade run user.NeuralAI-Mamba-K1-Q4_K_M

List all available models

lemonade list

Atomic Chat

NeuralAI-Mamba-K1 / tokenizer_config.json

Subject-Emu-5259

NeuralAI-Mamba-K1: push fine-tuned weights (LoRA merged)

2d2bd8d verified 12 days ago

Raw

History Blame Contribute Delete

529 Bytes

	{
	"add_prefix_space": false,
	"backend": "tokenizers",
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"errors": "replace",
	"is_local": false,
	"local_files_only": false,
	"max_length": 1024,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|endoftext\|>",
	"stride": 0,
	"tokenizer_class": "GPTNeoXTokenizer",
	"trim_offsets": true,
	"truncation_side": "right",
	"truncation_strategy": "longest_first",
	"unk_token": "<\|endoftext\|>"
	}