Instructions to use rumik-ai/rumik-oss-1-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use rumik-ai/rumik-oss-1-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir rumik-oss-1-mlx-4bit rumik-ai/rumik-oss-1-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "_sliding_window_pattern": 4, | |
| "architectures": [ | |
| "RumikOSSForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_end_token_id": 277394, | |
| "audio_start_token_id": 277393, | |
| "bos_token_id": 2, | |
| "codebook_size": 2048, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 3, | |
| "first_unit_id": 261008, | |
| "frame_rate_hz": 12.5, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "last_unit_id": 277391, | |
| "layer_norm_eps": 1e-05, | |
| "layer_switch": 4, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "logit_scale": 1.0, | |
| "max_position_embeddings": 8192, | |
| "model_type": "rumik_oss", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 4, | |
| "num_quantizers": 8, | |
| "order_of_interleaved_layers": "local_attn_first", | |
| "pad_token_id": 0, | |
| "position_embedding_type": "rope_gptj", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "rope_scaling": null, | |
| "rope_theta": 50000, | |
| "rotary_pct": 1.0, | |
| "sliding_window": 4096, | |
| "sliding_window_pattern": 4, | |
| "speakers": [ | |
| "Ira", | |
| "Aisha", | |
| "Siya", | |
| "Zoya" | |
| ], | |
| "text_start_token_id": 277392, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.57.6", | |
| "use_cache": true, | |
| "use_embedding_sharing": true, | |
| "use_gated_activation": true, | |
| "use_parallel_block": true, | |
| "use_parallel_embedding": false, | |
| "use_qk_norm": false, | |
| "vocab_size": 277404 | |
| } | |