| { |
| "_name_or_path": "YvanCarre/InkubaLM-multitask", |
| "adapters": { |
| "adapters": { |
| "machine-translation": "26cd1b10db746518", |
| "sentiment-analysis": "seq_bn", |
| "xnli": "seq_bn" |
| }, |
| "config_map": { |
| "26cd1b10db746518": { |
| "adapter_residual_before_ln": false, |
| "cross_adapter": false, |
| "dropout": 0.0, |
| "factorized_phm_W": true, |
| "factorized_phm_rule": false, |
| "hypercomplex_nonlinearity": "glorot-uniform", |
| "init_weights": "bert", |
| "inv_adapter": null, |
| "inv_adapter_reduction_factor": null, |
| "is_parallel": false, |
| "learn_phm": true, |
| "leave_out": [], |
| "ln_after": false, |
| "ln_before": false, |
| "mh_adapter": false, |
| "non_linearity": "relu", |
| "original_ln_after": true, |
| "original_ln_before": true, |
| "output_adapter": true, |
| "phm_bias": true, |
| "phm_c_init": "normal", |
| "phm_dim": 4, |
| "phm_init_range": 0.0001, |
| "phm_layer": false, |
| "phm_rank": 1, |
| "reduction_factor": 8, |
| "residual_before_ln": true, |
| "scaling": 1.0, |
| "shared_W_phm": false, |
| "shared_phm_rule": true, |
| "stochastic_depth": 0.0, |
| "use_gating": false |
| } |
| }, |
| "fusion_config_map": {}, |
| "fusion_name_map": {}, |
| "fusions": {} |
| }, |
| "architectures": [ |
| "LlamaAdapterModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoModelForCausalLM": "lelapa/InkubaLM-0.4B--vulavulaslm.VulavulaLlamaForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 5632, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "max_position_embeddings": 2048, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 8, |
| "num_key_value_heads": 32, |
| "prediction_heads": { |
| "default": { |
| "activation_function": null, |
| "bias": false, |
| "dropout_prob": null, |
| "embedding_size": 2048, |
| "head_type": "causal_lm", |
| "label2id": null, |
| "layer_norm": false, |
| "layers": 1, |
| "shift_labels": true, |
| "vocab_size": 61788 |
| }, |
| "machine-translation": { |
| "activation_function": "gelu", |
| "bias": true, |
| "dropout_prob": null, |
| "embedding_size": 2048, |
| "head_type": "causal_lm", |
| "label2id": null, |
| "layer_norm": true, |
| "layers": 2, |
| "shift_labels": true, |
| "vocab_size": 61788 |
| }, |
| "sentiment-analysis": { |
| "activation_function": "tanh", |
| "bias": true, |
| "dropout_prob": null, |
| "head_type": "classification", |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "layers": 2, |
| "num_labels": 3, |
| "use_pooler": false |
| }, |
| "xnli": { |
| "activation_function": "tanh", |
| "bias": true, |
| "dropout_prob": null, |
| "head_type": "classification", |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "layers": 2, |
| "num_labels": 3, |
| "use_pooler": false |
| } |
| }, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "float16", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.47.1", |
| "use_cache": true, |
| "vocab_size": 61788 |
| } |
|
|
