{ | |
"_name_or_path": "EleutherAI/pythia-70m-deduped", | |
"architectures": [ | |
"GPTNeoXForCausalLM" | |
], | |
"attention_bias": true, | |
"attention_dropout": 0.0, | |
"bos_token_id": 0, | |
"classifier_dropout": 0.1, | |
"eos_token_id": 0, | |
"hidden_act": "gelu", | |
"hidden_dropout": 0.0, | |
"hidden_size": 512, | |
"initializer_range": 0.02, | |
"intermediate_size": 2048, | |
"layer_norm_eps": 1e-05, | |
"max_position_embeddings": 2048, | |
"model_type": "gpt_neox", | |
"num_attention_heads": 8, | |
"num_hidden_layers": 6, | |
"quantization_config": { | |
"bits": 8, | |
"damp_percent": 0.1, | |
"dataset": "wikitext2", | |
"desc_act": false, | |
"group_size": 128, | |
"modules_in_block_to_quantize": null, | |
"quant_method": "gptq", | |
"sym": true, | |
"true_sequential": true | |
}, | |
"rope_scaling": null, | |
"rotary_emb_base": 10000, | |
"rotary_pct": 0.25, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.41.2", | |
"use_cache": true, | |
"use_parallel_residual": true, | |
"vocab_size": 50304 | |
} | |