mpt-7b-bf16-sharded / config.json
ybelkada's picture
ybelkada HF staff
Upload MptForCausalLM
3bb5c99
{
"_commit_hash": "72e5f594ce36f9cabfa2a9fd8f58b491eb467ee7",
"_name_or_path": "mosaicml/mpt-7b",
"architectures": [
"MptForCausalLM"
],
"attn_config": {
"_name_or_path": "",
"add_cross_attention": false,
"alibi": true,
"alibi_bias_max": 8,
"architectures": null,
"attn_impl": "torch",
"attn_pdrop": 0,
"attn_type": "multihead_attention",
"attn_uses_sequence_id": false,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"clip_qkv": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"prefix_lm": false,
"problem_type": null,
"pruned_heads": {},
"qk_ln": false,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"softmax_scale": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.32.0.dev0",
"typical_p": 1.0,
"use_bfloat16": false
},
"auto_map": {
"AutoConfig": "mosaicml/mpt-7b--configuration_mpt.MPTConfig",
"AutoModelForCausalLM": "mosaicml/mpt-7b--modeling_mpt.MPTForCausalLM"
},
"d_model": 4096,
"emb_pdrop": 0,
"embedding_fraction": 1.0,
"expansion_ratio": 4,
"init_config": {
"emb_init_std": null,
"emb_init_uniform_lim": null,
"fan_mode": "fan_in",
"init_div_is_residual": true,
"init_gain": 0,
"init_nonlinearity": "relu",
"init_std": 0.02,
"name": "kaiming_normal_",
"verbose": 0
},
"init_device": "cpu",
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"learned_pos_emb": true,
"logit_scale": null,
"max_seq_len": 2048,
"model_type": "mpt",
"n_heads": 32,
"n_layers": 32,
"no_bias": true,
"norm_type": "low_precision_layernorm",
"resid_pdrop": 0,
"tokenizer_name": "EleutherAI/gpt-neox-20b",
"torch_dtype": "bfloat16",
"transformers_version": "4.28.1",
"use_cache": false,
"verbose": 0,
"vocab_size": 50432
}