| { | |
| "architectures": [ | |
| "ZhinaoForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attn_dropout_prob": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "configuration_zhinao.ZhinaoConfig", | |
| "AutoModelForCausalLM": "modeling_zhinao.ZhinaoForCausalLM" | |
| }, | |
| "bf16": true, | |
| "emb_dropout_prob": 0.1, | |
| "flah-attn_version": "2.5.5", | |
| "fp16": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.01, | |
| "intermediate_size": 13056, | |
| "log_logit": false, | |
| "max_position_embeddings": 36000, | |
| "message": { | |
| "from": "", | |
| "model_size": "7B-gqa" | |
| }, | |
| "model_max_length": 36000, | |
| "model_type": "zhinao", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": null, | |
| "cache_block_outputs": true, | |
| "damp_percent": 0.01, | |
| "dataset": null, | |
| "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 | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "switch": 0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.0", | |
| "use_cache": false, | |
| "use_flash_attn": true, | |
| "use_focal": false, | |
| "use_loss_weight": false, | |
| "use_pack_loss": false, | |
| "vocab_size": 158464 | |
| } | |