codegen16b_sven / config.json
k1h0's picture
Upload folder using huggingface_hub
dbe293b verified
{
"_attn_implementation_autoset": true,
"_name_or_path": "Salesforce/codegen2-16B_P",
"activation_function": "gelu_new",
"architectures": [
"CodeGenForCausalLM"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "Salesforce/codegen2-16B_P--configuration_codegen.CodeGenConfig",
"AutoModel": "Salesforce/codegen2-16B_P--modeling_codegen.CodeGenModel",
"AutoModelForCausalLM": "Salesforce/codegen2-16B_P--modeling_codegen.CodeGenForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "codegen",
"n_control": 2,
"n_ctx": 2048,
"n_embd": 6144,
"n_head": 24,
"n_inner": null,
"n_layer": 34,
"n_positions": 2048,
"n_prefix_token": 12,
"prefix_dropout": 0.1,
"resid_pdrop": 0.0,
"rotary_dim": 64,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50,
"temperature": 1.0
}
},
"tie_word_embeddings": false,
"tokenizer_class": "GPT2Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.48.3",
"use_cache": true,
"vocab_size": 51200
}