|
{ |
|
"_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": { |
|
"batch_size": 1, |
|
"bits": 3, |
|
"block_name_to_quantize": "gpt_neox.layers", |
|
"damp_percent": 0.1, |
|
"dataset": "wikitext2", |
|
"desc_act": false, |
|
"disable_exllama": false, |
|
"group_size": 128, |
|
"model_seqlen": 4096, |
|
"module_name_preceding_first_block": [ |
|
"gpt_neox.embed_in", |
|
"gpt_neox.emb_dropout" |
|
], |
|
"pad_token_id": null, |
|
"quant_method": "gptq", |
|
"sym": true, |
|
"true_sequential": true, |
|
"use_cuda_fp16": true |
|
}, |
|
"rope_scaling": null, |
|
"rotary_emb_base": 10000, |
|
"rotary_pct": 0.25, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.44.0", |
|
"use_cache": true, |
|
"use_parallel_residual": true, |
|
"vocab_size": 50304 |
|
} |
|
|