hf-transformers-bot's picture
Update tiny models for MiniMaxM3VLForCausalLM
ed95f96 verified
Raw
History Blame Contribute Delete
1.36 kB
{
"architectures": [
"MiniMaxM3VLForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 200019,
"dense_intermediate_size": 128,
"dtype": "float32",
"eos_token_id": 200020,
"head_dim": 32,
"hidden_act": "silu",
"hidden_size": 32,
"index_block_size": 8,
"index_head_dim": 16,
"index_local_blocks": 1,
"index_n_heads": 2,
"index_topk_blocks": 4,
"initializer_range": 0.02,
"intermediate_size": 64,
"is_decoder": true,
"layer_types": [
"full_attention",
"minimax_m3_sparse"
],
"max_position_embeddings": 512,
"mlp_layer_types": [
"dense",
"sparse"
],
"model_type": "minimax_m3_vl_text",
"n_shared_experts": 1,
"num_attention_heads": 4,
"num_experts_per_tok": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"num_local_experts": 4,
"output_router_logits": false,
"pad_token_id": 200000,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"partial_rotary_factor": 0.5,
"rope_theta": 5000000.0,
"rope_type": "default"
},
"rotary_dim": 16,
"routed_scaling_factor": 2.0,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"shared_intermediate_size": 32,
"swiglu_alpha": 1.702,
"swiglu_limit": 7.0,
"tie_word_embeddings": false,
"transformers_version": "5.16.0.dev0",
"use_cache": true,
"use_routing_bias": true,
"vocab_size": 200061
}