Text Generation
Safetensors
MLX
mlx-lm
deepseek_v2
apple-silicon
tencent
youtu
reasoning
mla
conversational
custom_code
Instructions to use mlx-community/Youtu-LLM-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Youtu-LLM-2B with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/Youtu-LLM-2B") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use mlx-community/Youtu-LLM-2B with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Youtu-LLM-2B"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "mlx-community/Youtu-LLM-2B" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use mlx-community/Youtu-LLM-2B with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Youtu-LLM-2B"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default mlx-community/Youtu-LLM-2B
Run Hermes
hermes
- MLX LM
How to use mlx-community/Youtu-LLM-2B with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "mlx-community/Youtu-LLM-2B"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mlx-community/Youtu-LLM-2B" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/Youtu-LLM-2B", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "YoutuForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_youtu.YoutuConfig", | |
| "AutoModel": "modeling_youtu.YoutuModel", | |
| "AutoModelForCausalLM": "modeling_youtu.YoutuForCausalLM" | |
| }, | |
| "bos_token_id": 128000, | |
| "embedding_initializer_range": null, | |
| "eos_token_id": 128001, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": null, | |
| "intermediate_size": 6144, | |
| "kv_lora_rank": 512, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "deepseek_v2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 16, | |
| "q_lora_rank": 1536, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": { | |
| "type": "yarn", | |
| "factor": 1.0, | |
| "mscale_all_dim": 0 | |
| }, | |
| "rope_theta": 1600000, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.56.0", | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 128256 | |
| } |