hf-transformers-bot HF Staff
Update tiny models for MiniMaxForSequenceClassification
600d68f verified | { | |
| "architectures": [ | |
| "MiniMaxForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "block_size": 3, | |
| "bos_token_id": 200019, | |
| "dtype": "float32", | |
| "eos_token_id": 200020, | |
| "full_attn_alpha_factor": 1, | |
| "full_attn_beta_factor": 1, | |
| "head_dim": 16, | |
| "hidden_act": "gelu", | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "layer_types": [ | |
| "full_attention", | |
| "linear_attention" | |
| ], | |
| "linear_attn_alpha_factor": 1, | |
| "linear_attn_beta_factor": 1, | |
| "max_position_embeddings": 512, | |
| "mlp_alpha_factor": 1, | |
| "mlp_beta_factor": 1, | |
| "model_type": "minimax", | |
| "num_attention_heads": 2, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 200026 | |
| } | |