| { | |
| "architectures": [ | |
| "SmolLM3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": 128012, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 65536, | |
| "max_window_layers": 28, | |
| "mlp_bias": false, | |
| "model_type": "smollm3", | |
| "no_rope_layer_interval": 4, | |
| "no_rope_layers": [ | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1, | |
| 1, | |
| 0 | |
| ], | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 128004, | |
| "pretraining_tp": 2, | |
| "quantization_config": { | |
| "include_input_output_embeddings": false, | |
| "modules_to_not_convert": [], | |
| "quant_method": "torchao", | |
| "quant_type": { | |
| "default": { | |
| "_data": { | |
| "module_fqn_to_config": { | |
| "_default": { | |
| "_data": { | |
| "act_mapping_type": { | |
| "_data": "ASYMMETRIC", | |
| "_type": "MappingType" | |
| }, | |
| "layout": { | |
| "_data": {}, | |
| "_type": "QDQLayout", | |
| "_version": 1 | |
| }, | |
| "weight_dtype": { | |
| "_data": "int4", | |
| "_type": "torch.dtype" | |
| }, | |
| "weight_granularity": { | |
| "_data": { | |
| "group_size": 32 | |
| }, | |
| "_type": "PerGroup", | |
| "_version": 1 | |
| }, | |
| "weight_mapping_type": { | |
| "_data": "SYMMETRIC", | |
| "_type": "MappingType" | |
| }, | |
| "weight_scale_dtype": { | |
| "_data": "bfloat16", | |
| "_type": "torch.dtype" | |
| } | |
| }, | |
| "_type": "Int8DynamicActivationIntxWeightConfig", | |
| "_version": 1 | |
| }, | |
| "model.embed_tokens": { | |
| "_data": { | |
| "granularity": { | |
| "_data": { | |
| "axis": 0 | |
| }, | |
| "_type": "PerAxis", | |
| "_version": 1 | |
| }, | |
| "layout": { | |
| "_data": {}, | |
| "_type": "QDQLayout", | |
| "_version": 1 | |
| }, | |
| "mapping_type": { | |
| "_data": "SYMMETRIC", | |
| "_type": "MappingType" | |
| }, | |
| "scale_dtype": null, | |
| "weight_dtype": { | |
| "_data": "int8", | |
| "_type": "torch.dtype" | |
| } | |
| }, | |
| "_type": "IntxWeightOnlyConfig", | |
| "_version": 1 | |
| } | |
| } | |
| }, | |
| "_type": "ModuleFqnToConfig", | |
| "_version": 1 | |
| } | |
| }, | |
| "quant_type_kwargs": { | |
| "include_embedding": true | |
| }, | |
| "untie_embedding_weights": true | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.54.0.dev0", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 128256 | |
| } | |