Instructions to use iamEvanYT/K2-Horizon-MoVA-36B-A4B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use iamEvanYT/K2-Horizon-MoVA-36B-A4B-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir K2-Horizon-MoVA-36B-A4B-MLX-4bit iamEvanYT/K2-Horizon-MoVA-36B-A4B-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "architectures": [ | |
| "K2HorizonForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_gate_func": "softplus", | |
| "auto_map": { | |
| "AutoConfig": "configuration_k2_horizon.K2HorizonConfig", | |
| "AutoModel": "modeling_k2_horizon.K2HorizonModel", | |
| "AutoModelForCausalLM": "modeling_k2_horizon.K2HorizonForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "decoder_sparse_step": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layernorm_num_groups": 2, | |
| "max_position_embeddings": 524288, | |
| "mlp_only_layers": [ | |
| 0, | |
| 1, | |
| 2 | |
| ], | |
| "model_type": "k2_horizon", | |
| "moe_gate_bias": true, | |
| "moe_intermediate_size": 768, | |
| "mova_num_experts": 64, | |
| "mova_num_experts_per_tok": 4, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_experts": 100, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "num_shared_experts": 1, | |
| "output_router_logits": false, | |
| "pad_token_id": null, | |
| "query_key_norm": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_head_dim": 128, | |
| "rope_parameters": { | |
| "rope_theta": 10000000.0, | |
| "rope_type": "default" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "router_scaling_factor": 2.5, | |
| "router_score_func": "sigmoid", | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.13.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 250624, | |
| "model_file": "k2_horizon.py", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| } | |
| } | |