| { |
| "architectures": [ |
| "Lfm2MoeForCausalLM" |
| ], |
| "bos_token_id": 124894, |
| "conv_L_cache": 3, |
| "conv_bias": false, |
| "dtype": "bfloat16", |
| "eos_token_id": 124900, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 7168, |
| "layer_types": [ |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv" |
| ], |
| "max_position_embeddings": 128000, |
| "model_type": "lfm2_moe", |
| "moe_intermediate_size": 1792, |
| "norm_eps": 1e-05, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_dense_layers": 2, |
| "num_experts": 32, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 8, |
| "pad_token_id": 124893, |
| "rope_parameters": { |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "routed_scaling_factor": 1.0, |
| "transformers_version": "5.0.0.dev0", |
| "use_cache": true, |
| "use_expert_bias": true, |
| "vocab_size": 128000, |
| "transformers.js_config": { |
| "use_external_data_format": { |
| "model.onnx": 23, |
| "model_fp16.onnx": 10, |
| "model_q4.onnx": 3, |
| "model_q4f16.onnx": 3, |
| "model_q8.onnx": 22 |
| }, |
| "kv_cache_dtype": { |
| "fp16": "float16", |
| "q4f16": "float16" |
| } |
| } |
| } |
|
|
