| { |
| "architectures": [ |
| "ApertusForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 68, |
| "hidden_act": "xielu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 4096, |
| "mlp_bias": false, |
| "model_type": "apertus", |
| "num_attention_heads": 24, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 8, |
| "pad_token_id": 10, |
| "post_norm": false, |
| "qk_norm": true, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "token", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "float-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.15.1.a20260428" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 500000.0, |
| "rope_type": "default" |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.7.0", |
| "use_cache": false, |
| "vocab_size": 131072 |
| } |
