| { |
| "architectures": [ |
| "MiniCPMSALAForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_use_output_gate": true, |
| "attn_use_rope": false, |
| "auto_map": { |
| "AutoConfig": "configuration_minicpm_sala.MiniCPMSALAConfig", |
| "AutoModel": "modeling_minicpm_sala.MiniCPMSALAModel", |
| "AutoModelForCausalLM": "modeling_minicpm_sala.MiniCPMSALAForCausalLM", |
| "AutoModelForSeq2SeqLM": "modeling_minicpm_sala.MiniCPMSALAForCausalLM", |
| "AutoModelForSequenceClassification": "modeling_minicpm_sala.MiniCPMSALAForSequenceClassification" |
| }, |
| "bos_token_id": 1, |
| "dim_model_base": 256, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 2, |
| 73440 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.1, |
| "intermediate_size": 16384, |
| "lightning_head_dim": 128, |
| "lightning_nh": 32, |
| "lightning_nkv": 32, |
| "lightning_scale": "1/sqrt(d)", |
| "lightning_use_rope": true, |
| "max_position_embeddings": 524288, |
| "mixer_types": [ |
| "minicpm4", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "minicpm4", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "minicpm4", |
| "minicpm4", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "minicpm4", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "lightning-attn", |
| "minicpm4", |
| "minicpm4", |
| "minicpm4" |
| ], |
| "model_type": "minicpm_sala", |
| "mup_denominator": 32, |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 2, |
| "pad_token_id": 2, |
| "pretraining_tp": 1, |
| "qk_norm": true, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "dynamic": { |
| "+:model\\.model\\.layers\\.0\\..*": { |
| "bits": 8 |
| } |
| }, |
| "format": "gptq", |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": true, |
| "auto_forward_data_parallel": true, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "failsafe": { |
| "smooth": { |
| "group_size_threshold": 128, |
| "k": 2.75, |
| "type": "mad" |
| }, |
| "strategy": "rtn", |
| "threshold": "0.5%" |
| }, |
| "gc_mode": "interval", |
| "gptaq": null, |
| "hessian": { |
| "chunk_bytes": null, |
| "chunk_size": null, |
| "staging_dtype": "float32" |
| }, |
| "mock_quantization": false, |
| "mse": 0.0, |
| "offload_to_disk": true, |
| "offload_to_disk_path": "./gptqmodel_offload/hqdpgrum-rkaakpxx/", |
| "pack_impl": "cpu", |
| "quantizer": [ |
| "gptqmodel:5.7.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "vram_strategy": "exclusive", |
| "wait_for_submodule_finalizers": false |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "scale_depth": 1.4, |
| "scale_emb": 12, |
| "shift_labels": true, |
| "sparse_config": { |
| "block_size": 64, |
| "dense_len": 8192, |
| "init_blocks": 1, |
| "kernel_size": 32, |
| "kernel_stride": 16, |
| "topk": 64, |
| "use_nope": false, |
| "window_size": 2048 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "use_output_gate": true, |
| "use_output_norm": true, |
| "vocab_size": 73448 |
| } |
|
|
