{ "_name_or_path": "/tmp/tmplndb8c2a", "architectures": [ "MPTForCausalLM" ], "attn_config": { "alibi": true, "alibi_bias_max": 8, "attn_impl": "torch", "attn_pdrop": 0, "attn_type": "multihead_attention", "attn_uses_sequence_id": false, "clip_qkv": null, "prefix_lm": false, "qk_gn": false, "qk_ln": false, "rope": false, "rope_dail_config": { "pos_idx_in_fp32": true, "type": "original", "xpos_scale_base": 512 }, "rope_hf_config": { "factor": 1.0, "type": "no_scaling" }, "rope_impl": "dail", "rope_theta": 10000, "sliding_window_size": -1, "softmax_scale": null }, "auto_map": { "AutoConfig": "configuration_mpt.MPTConfig", "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM" }, "d_model": 4096, "emb_pdrop": 0, "embedding_fraction": 1.0, "expansion_ratio": 4, "fc_type": "torch", "ffn_config": { "fc_type": "torch", "ffn_type": "mptmlp" }, "init_config": { "emb_init_std": null, "emb_init_uniform_lim": null, "fan_mode": "fan_in", "init_div_is_residual": true, "init_gain": 0.0, "init_nonlinearity": "relu", "init_std": null, "name": "kaiming_normal_", "verbose": 0 }, "init_device": "cpu", "learned_pos_emb": false, "logit_scale": null, "max_seq_len": 8192, "model_type": "mpt", "n_heads": 32, "n_layers": 32, "no_bias": true, "norm_type": "low_precision_layernorm", "quantization_config": { "bnb_4bit_compute_dtype": "bfloat16", "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": [ "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "resid_pdrop": 0, "tokenizer_name": "EleutherAI/gpt-neox-20b", "torch_dtype": "float16", "transformers_version": "4.37.1", "use_cache": false, "use_pad_tok_in_ffn": true, "verbose": 0, "vocab_size": 50432 }