Download config.json from kerzgrr/Haiku-base: direct link, hf CLI and curl.
- Browser
- Download file 1.95 kB
-
https://huggingface.co/kerzgrr/Haiku-base/resolve/main/config.json
- Command line
-
hf download hf://kerzgrr/Haiku-base/config.json
-
curl -L -o config.json https://huggingface.co/kerzgrr/Haiku-base/resolve/main/config.json
1.95 kB
| { | |
| "allow_negative_eigenvalues": false, | |
| "architecture": "HaikuForCausalLM", | |
| "architectures": [ | |
| "HaikuForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_head_dim": 128, | |
| "attention_layer_type": "gated_mla", | |
| "bos_token_id": 0, | |
| "checkpoint_step": 8400, | |
| "eos_token_id": 1, | |
| "full_attention_interval": 4, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3840, | |
| "kda_lower_bound": -5.0, | |
| "kda_safe_gate": true, | |
| "layer_types": [ | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla", | |
| "kda", | |
| "kda", | |
| "kda", | |
| "gated_mla" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_expand_v": 1.0, | |
| "linear_head_dim": 128, | |
| "linear_layer_type": "kda", | |
| "linear_num_heads": 8, | |
| "linear_num_value_heads": 8, | |
| "max_position_embeddings": 32768, | |
| "mla_kv_lora_rank": 256, | |
| "mla_q_lora_rank": 512, | |
| "mla_qk_nope_head_dim": 128, | |
| "mla_v_head_dim": 128, | |
| "mlp_activation": "situ_glu", | |
| "model_family": "Haiku", | |
| "model_name": "Haiku-base", | |
| "model_type": "haiku", | |
| "mtp_adapter_rank": 128, | |
| "mtp_loss_weight": 0.2, | |
| "mtp_num_heads": 2, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "partial_rotary_factor": 0.5, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "shared_layer_indices": [], | |
| "situ_gate_cap": 4.0, | |
| "situ_up_cap": 25.0, | |
| "stage": "pretrain", | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "training_sequence_length": 2048, | |
| "transformers_version": "4.45.0", | |
| "unk_token_id": 3, | |
| "use_block_attn_res": true, | |
| "vocab_size": 65536, | |
| "weights": "ema" | |
| } | |