moss-moon-003-sft-int4 / config.json
txsun's picture
Upload config.json with huggingface_hub
9ed415a
{
"_name_or_path": "moss-moon-003-sft-int4",
"activation_function": "gelu_new",
"architectures": [
"MossForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_moss.MossConfig",
"AutoModel": "modeling_moss.MossModel",
"AutoModelForCausalLM": "modeling_moss.MossForCausalLM"
},
"attn_pdrop": 0.0,
"bos_token_id": 106028,
"embd_pdrop": 0.0,
"eos_token_id": 106068,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "moss",
"n_ctx": 2048,
"n_embd": 6144,
"n_head": 24,
"n_inner": null,
"n_layer": 34,
"n_positions": 2048,
"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": "float16",
"transformers_version": "4.25.1",
"use_cache": true,
"vocab_size": 107008,
"wbits": 4,
"groupsize": 128
}