zephyr-7b-sft-full / config.json
ZHENGRAN's picture
Training in progress, step 300
058e196 verified
{
"_name_or_path": "/nvme/share/checkpoints/codeshell/shell/cpt_shell_100b_20240212/iter_0012715/hf",
"activation_function": "gelu_pytorch_tanh",
"architectures": [
"CodeShellForCausalLM"
],
"attention_softmax_in_fp32": true,
"attn_pdrop": 0.1,
"auto_map": {
"AutoConfig": "configuration_codeshell.CodeShellConfig",
"AutoModelForCausalLM": "modeling_codeshell.CodeShellForCausalLM"
},
"bos_token_id": 70000,
"embd_pdrop": 0.1,
"eos_token_id": 70000,
"group_query_attention": true,
"inference_runner": 0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"max_batch_size": null,
"max_sequence_length": null,
"model_type": "codeshell",
"n_embd": 4096,
"n_head": 32,
"n_inner": 16384,
"n_layer": 42,
"n_positions": 8192,
"num_query_groups": 8,
"pad_key_length": true,
"position_embedding_type": "rope",
"pre_allocate_kv_cache": false,
"resid_pdrop": 0.1,
"rope_scaling": null,
"scale_attention_softmax_in_fp32": true,
"scale_attn_weights": true,
"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": "4.36.2",
"use_cache": false,
"validate_runner_input": true,
"vocab_size": 70144
}