lapp0's picture
Training in progress, step 12375
7077291 verified
raw
history blame
1.48 kB
{
"_name_or_path": "roneneldan/TinyStories-33M",
"activation_function": "gelu_new",
"architectures": [
"GPTNeoForCausalLM"
],
"attention_dropout": 0,
"attention_layers": [
"global",
"local",
"global",
"local"
],
"attention_types": [
[
[
"global",
"local"
],
2
]
],
"bos_token_id": 50256,
"classifier_dropout": 0.1,
"embed_dropout": 0,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": null,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neo",
"num_heads": 16,
"num_layers": 4,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"resid_dropout": 0,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.0",
"use_cache": true,
"vocab_size": 50257,
"window_size": 256
}