Instructions to use Aryagm/HRM-Text-1B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Aryagm/HRM-Text-1B-MLX-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Aryagm/HRM-Text-1B-MLX-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use Aryagm/HRM-Text-1B-MLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "Aryagm/HRM-Text-1B-MLX-4bit" --prompt "Once upon a time"
| { | |
| "model_type": "hrm_text", | |
| "architectures": [ | |
| "HrmTextForCausalLM" | |
| ], | |
| "vocab_size": 65536, | |
| "hidden_size": 1536, | |
| "intermediate_size": 4096, | |
| "num_hidden_layers": 16, | |
| "num_attention_heads": 12, | |
| "num_key_value_heads": 12, | |
| "head_dim": 128, | |
| "H_cycles": 2, | |
| "L_cycles": 3, | |
| "L_bp_cycles": [ | |
| 0, | |
| 3 | |
| ], | |
| "max_position_embeddings": 4096, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "initializer_range": 0.025515518153991442, | |
| "embedding_scale": 39.191835884530846, | |
| "prefix_lm": true, | |
| "pad_token_id": 5, | |
| "bos_token_id": 6, | |
| "eos_token_id": 11, | |
| "auto_map": { | |
| "AutoConfig": "configuration_hrm_text.HrmTextConfig", | |
| "AutoModel": "modeling_hrm_text.HrmTextModel", | |
| "AutoModelForCausalLM": "modeling_hrm_text.HrmTextForCausalLM" | |
| }, | |
| "mlx_format_version": 1, | |
| "mlx_dtype": "bfloat16" | |
| } | |