MobileLLM-Pro / config.json
camenduru's picture
thanks to facebook ❤
7f64a5a verified
{
"architectures": [
"MobileLLMP1ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_mobilellm_p1.MobileLLMP1TextConfig",
"AutoModelForCausalLM": "modeling_mobilellm_p1.MobileLLMP1ForCausalLM"
},
"attention_bias": false,
"attention_chunk_size": 8192,
"attention_dropout": 0.0,
"attn_scale": 0.1,
"bos_token_id": 200000,
"eos_token_id": [
200001,
200007,
200008
],
"pad_token_id": 200018,
"for_llm_compressor": false,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1280,
"initializer_range": 0.02,
"intermediate_size": 6144,
"intermediate_size_mlp": 6144,
"layer_types": [
"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",
"full_attention"
],
"sliding_window": 512,
"max_position_embeddings": 131072,
"model_type": "llama4_text",
"moe_layers": [],
"no_rope_layers": [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
],
"num_attention_heads": 20,
"num_experts_per_tok": 0,
"num_hidden_layers": 30,
"num_key_value_heads": 4,
"num_local_experts": 0,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 16.0,
"high_freq_factor": 1.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.0.dev0",
"use_cache": true,
"use_qk_norm": false,
"vocab_size": 202048
}