| { | |
| "vocab_size": 49152, | |
| "max_position_embeddings": 16384, | |
| "hidden_size": 4608, | |
| "intermediate_size": 18432, | |
| "num_hidden_layers": 32, | |
| "num_attention_heads": 36, | |
| "sliding_window": 4096, | |
| "use_bias": true, | |
| "num_key_value_heads": 4, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "initializer_range": 0.018042, | |
| "norm_epsilon": 1e-05, | |
| "use_cache": true, | |
| "rope_theta": 1000000, | |
| "attention_dropout": 0.0, | |
| "residual_dropout": 0.0, | |
| "embedding_dropout": 0.0, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "output_attentions": false, | |
| "torchscript": false, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": false, | |
| "tf_legacy_loss": false, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "architectures": [ | |
| "Starcoder2ForCausalLM" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": 0, | |
| "pad_token_id": null, | |
| "eos_token_id": 0, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "_name_or_path": "/Users/muhtashamoblokulov/.cache/huggingface/hub/models--bigcode--starcoder2-7b/snapshots/fdb7db8a394942ed7879032fadad91ccb44fc74e", | |
| "transformers_version": "4.39.0.dev0", | |
| "activation_function": "gelu", | |
| "attention_softmax_in_fp32": true, | |
| "layer_norm_epsilon": 1e-05, | |
| "mlp_type": "default", | |
| "model_type": "starcoder2", | |
| "norm_type": "layer_norm", | |
| "scale_attention_softmax_in_fp32": true, | |
| "scale_attn_weights": true, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4 | |
| } | |
| } |