56b1328917
Model: princeton-nlp/lm-1.3B-select_30B_tokens_by-inverse_writing_style-top_k Source: Original Platform
29 lines
855 B
JSON
29 lines
855 B
JSON
{
|
|
"_name_or_path": "/projects/DANQIC/awettig/lm-data-selection/checkpoints/lm_princeton-nlp--Sheared-LLaMA-1.3b_bsz2048_lr5e-4to10pc_epochs1_warmup0.05_datasetslimpajama-1000_4000-seg1024-equidomain-writing_style-t0.0top30B",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 5504,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 16,
|
|
"pad_token_id": 0,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.35.0",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
}
|