bling-1.4b-0.1 / config.json
doberst's picture
Upload 4 files
4e1e91d
{ "model_name": "bling-1.4b-0.1",
"description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
"training_timestamp": "Mon Sep 25 20:31:36 2023",
"training_comments": "pythia-1.4b-v1.0",
"_name_or_path": "EleutherAI/pythia-1.4b-v0",
"transformers_version": "4.28.1",
"model_type": "gpt_neox",
"vocab_size": 50304,
"max_position_embeddings": 2048,
"hidden_size": 2048,
"num_hidden_layers": 24,
"num_attention_heads": 16,
"intermediate_size": 8192,
"hidden_act": "gelu",
"rotary_pct": 0.25,
"rotary_emb_base": 10000,
"initializer_range": 0.02,
"layer_norm_eps": 1e-05,
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": "float16",
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": false,
"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,
"chunk_size_feed_forward": 0,
"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": [
"GPTNeoXForCausalLM"
],
"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,
"use_cache": true,
"use_parallel_residual": true,
"trained": "custom training"
}