| { |
| "architectures": [ |
| "NcpSmolForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration.NcpSmolConfig", |
| "AutoModelForCausalLM": "modeling.NcpSmolForCausalLM" |
| }, |
| "backbone_config": { |
| "_name_or_path": "HuggingFaceTB/SmolLM2-135M", |
| "add_cross_attention": false, |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_implementation": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 0, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "float32", |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 0, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 576, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.041666666666666664, |
| "intermediate_size": 1536, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "is_llama_config": true, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 8192, |
| "min_length": 0, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 9, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 3, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "pretraining_tp": 1, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-05, |
| "rope_interleaved": false, |
| "rope_scaling": null, |
| "rope_theta": 100000, |
| "sep_token_id": null, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "transformers_version": "4.57.6", |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 49152 |
| }, |
| "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M", |
| "base_model_revision": "93efa2f097d58c2a74874c7e644dbc9b0cee75a2", |
| "chunk_size": 4, |
| "codebook_size": 64, |
| "concept_layers": 2, |
| "dtype": "float32", |
| "hidden_size": 576, |
| "insert_layer": 1, |
| "model_type": "ncp_smol", |
| "ncp_target": "continuous", |
| "ncp_weight": 1.0, |
| "num_attention_heads": 9, |
| "num_hidden_layers": 30, |
| "num_key_value_heads": 3, |
| "segments": 9, |
| "transformers_version": "4.57.6", |
| "use_cache": false, |
| "vocab_size": 49152, |
| "vq_weight": 1.0 |
| } |
|
|
