slim-qwen-extract-1.5b / config.json
doberst's picture
Upload 6 files
34f1032 verified
{
"aib_version": "model_archive_072424_qwen15_extract_eot_4",
"training_dataset": [
"extract2_new_031724_eot_2_9442.jsonl"
],
"training_timestamp": "Wed Jul 24 10:43:25 2024",
"training_comments": "qwen2-1.5b-extract-eot-072424-4",
"vocab_size": 151936,
"max_position_embeddings": 131072,
"hidden_size": 1536,
"intermediate_size": 8960,
"num_hidden_layers": 28,
"num_attention_heads": 12,
"use_sliding_window": false,
"sliding_window": 131072,
"max_window_layers": 28,
"num_key_value_heads": 2,
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"use_cache": true,
"rope_theta": 1000000.0,
"attention_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": [
"Qwen2ForCausalLM"
],
"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": 151643,
"pad_token_id": null,
"eos_token_id": 151643,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "Qwen/Qwen2-1.5B",
"transformers_version": "4.38.1",
"model_type": "qwen2",
"trained": "custom training"
}