File size: 1,444 Bytes
5a8a8f1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
{
"_name_or_path": "EleutherAI/pythia-31m",
"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": 256,
"initializer_range": 0.02,
"intermediate_size": 1024,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 8,
"num_hidden_layers": 6,
"partial_rotary_factor": 0.25,
"quantization_config": {
"amp": false,
"autoround_version": "0.4.0.dev",
"backend": "auto_round:gptq:exllamav2",
"bits": 4,
"data_type": "int",
"dataset": "NeelNanda/pile-10k",
"enable_minmax_tuning": true,
"enable_norm_bias_tuning": false,
"enable_quanted_input": true,
"gradient_accumulate_steps": 1,
"group_size": 128,
"iters": 200,
"low_gpu_mem_usage": false,
"lr": 0.005,
"minmax_lr": 0.005,
"nsamples": 128,
"quant_block_list": null,
"quant_method": "intel/auto-round",
"scale_dtype": "torch.float16",
"seqlen": 512,
"sym": true,
"train_bs": 4
},
"rope_scaling": null,
"rope_theta": 10000,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.45.2",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50304
}
|