Instructions to use mlabonne/NeuralBeagle14-7B-GGUF 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 mlabonne/NeuralBeagle14-7B-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 mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mlabonne/NeuralBeagle14-7B-GGUF: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 mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf mlabonne/NeuralBeagle14-7B-GGUF: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 mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use mlabonne/NeuralBeagle14-7B-GGUF with Ollama:
ollama run hf.co/mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use mlabonne/NeuralBeagle14-7B-GGUF with Docker Model Runner:
docker model run hf.co/mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
- Lemonade
How to use mlabonne/NeuralBeagle14-7B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mlabonne/NeuralBeagle14-7B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.NeuralBeagle14-7B-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Context Length?
What is the context length for this model?
related, what system prompt format do you recommend?
----- update ------
<|system|>
You are a helpful AI assistant. You answer questions correctly
<|user|>
{{ .Prompt }}
<|assistant|>
The context window can be taken from the llama.cpp output, but without the prompt template we are doomed
According to llama.cpp it's 32k
It's 8k I'll modify the config to reflect that.
Thank you!
related, what system prompt format do you recommend?
----- update ------
<|system|>
You are a helpful AI assistant. You answer questions correctly
<|user|>
{{ .Prompt }}
<|assistant|>
I use chatml by default but this is not supposed to be the right prompt template according to the tokens (Llama's chat template is). It still works so I'm careful about modifying anything (if it ain't broke...).
I think it would be great if you would always publish the context window size and the prompt template in the model card. Thanks.
I think it would be great if you would always publish the context window size and the prompt template in the model card. Thanks.
Yes, it's done. From now on, I'll try to provide this info for every model.
Yes, it's done. From now on, I'll try to provide this info for every model.
Awesome to hear! By the way, can you include the updated metadata in the gguf files themselves? I noticed that the 32k context metadata info messed with the automatic RoPE scaling for KoboldCPP. You are onto something with your model, so it would be much appreciated. Thanks! 🙂
Yes, I'm going to reupload all the GGUF files with the new version