Instructions to use aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit 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("aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit") 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
- MLX LM
How to use aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aimeri/spoomplesmaxx-mockingbird-36B-mlx-3bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
| { | |
| "architectures": [ | |
| "SeedOssForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.1, | |
| "attention_out_bias": false, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 524288, | |
| "mlp_bias": false, | |
| "model_type": "seed_oss", | |
| "num_attention_heads": 80, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 1, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine" | |
| }, | |
| "residual_dropout": 0.1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 10000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0", | |
| "use_cache": true, | |
| "vocab_size": 155136 | |
| } |