| { | |
| "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsdhkyhu_nhop2bfo6", | |
| "add_bias_linear": false, | |
| "add_qkv_bias": true, | |
| "apply_query_key_layer_scaling": true, | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "ChatGLMForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_softmax_in_fp32": true, | |
| "auto_map": { | |
| "AutoConfig": "configuration_chatglm.ChatGLMConfig", | |
| "AutoModel": "THUDM/LongWriter-glm4-9b--modeling_chatglm.ChatGLMForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration", | |
| "AutoModelForSeq2SeqLM": "THUDM/LongWriter-glm4-9b--modeling_chatglm.ChatGLMForConditionalGeneration", | |
| "AutoModelForSequenceClassification": "THUDM/LongWriter-glm4-9b--modeling_chatglm.ChatGLMForSequenceClassification" | |
| }, | |
| "bias_dropout_fusion": true, | |
| "classifier_dropout": null, | |
| "eos_token_id": [ | |
| 151329, | |
| 151336, | |
| 151338 | |
| ], | |
| "ffn_hidden_size": 13696, | |
| "fp32_residual_connection": false, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4096, | |
| "kv_channels": 128, | |
| "layernorm_epsilon": 1.5625e-07, | |
| "model_type": "chatglm", | |
| "multi_query_attention": true, | |
| "multi_query_group_num": 2, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_layers": 40, | |
| "original_rope": true, | |
| "pad_token_id": 151329, | |
| "padded_vocab_size": 151552, | |
| "post_layer_norm": true, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "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" | |
| }, | |
| "rmsnorm": true, | |
| "rope_ratio": 500, | |
| "seq_length": 1048576, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.42.4", | |
| "use_cache": true, | |
| "vocab_size": 151552 | |
| } | |