{ "_name_or_path": "core42/jais-13b-chat", "activation_function": "swiglu", "architectures": [ "JAISLMHeadModel" ], "attn_pdrop": 0.0, "auto_map": { "AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig", "AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel", "AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel", "AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering", "AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification", "AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification" }, "bos_token_id": 0, "embd_pdrop": 0.0, "embeddings_scale": 14.6, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "jais", "n_embd": 5120, "n_head": 40, "n_inner": 13653, "n_layer": 40, "n_positions": 2048, "pad_token_id": 0, "position_embedding_type": "alibi", "quantization_config": { "batch_size": 1, "bits": 4, "block_name_to_quantize": null, "cache_block_outputs": true, "damp_percent": 0.1, "dataset": "c4", "desc_act": false, "exllama_config": { "version": 1 }, "group_size": 128, "max_input_length": null, "model_seqlen": null, "module_name_preceding_first_block": null, "modules_in_block_to_quantize": null, "pad_token_id": null, "quant_method": "gptq", "sym": true, "tokenizer": null, "true_sequential": true, "use_cuda_fp16": false, "use_exllama": true }, "reorder_and_upcast_attn": false, "resid_pdrop": 0.0, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "scale_qk_dot_by_d": true, "torch_dtype": "float16", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 84992, "width_scale": 0.11100000000000002 }