| { |
| "architectures": [ |
| "GraniteMoeHybridForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_multiplier": 0.0078125, |
| "bos_token_id": 100257, |
| "dtype": "bfloat16", |
| "embedding_multiplier": 12, |
| "eos_token_id": 100257, |
| "hidden_act": "silu", |
| "hidden_size": 32, |
| "initializer_range": 0.1, |
| "intermediate_size": 128, |
| "layer_types": [ |
| "mamba", |
| "attention" |
| ], |
| "logits_scaling": 16, |
| "mamba_chunk_size": 256, |
| "mamba_conv_bias": true, |
| "mamba_d_conv": 4, |
| "mamba_d_head": 64, |
| "mamba_d_state": 128, |
| "mamba_expand": 256, |
| "mamba_n_groups": 1, |
| "mamba_n_heads": 128, |
| "mamba_proj_bias": false, |
| "max_position_embeddings": 131072, |
| "model_type": "granitemoehybrid", |
| "normalization_function": "rmsnorm", |
| "num_attention_heads": 2, |
| "num_experts_per_tok": 10, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "num_local_experts": 72, |
| "output_router_logits": false, |
| "pad_token_id": 100256, |
| "position_embedding_type": "nope", |
| "residual_multiplier": 0.22, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 10000, |
| "rope_type": "default" |
| }, |
| "router_aux_loss_coef": 0.0, |
| "shared_intermediate_size": 128, |
| "tie_word_embeddings": true, |
| "time_step_limit": [ |
| 0.0, |
| { |
| "__float__": "Infinity" |
| } |
| ], |
| "time_step_max": 0.1, |
| "time_step_min": 0.001, |
| "transformers_version": "5.3.0.dev0", |
| "use_cache": true, |
| "vocab_size": 100352, |
| "transformers.js_config": { |
| "use_external_data_format": { |
| "model.onnx": 1, |
| "model_fp16.onnx": 1 |
| }, |
| "kv_cache_dtype": { |
| "q4f16": "float16", |
| "fp16": "float16" |
| } |
| } |
| } |