| { | |
| "_name_or_path": "/models//cogvlm2-llama3-chat-19B", | |
| "architectures": [ | |
| "CogVLMForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_cogvlm.CogVLMConfig", | |
| "AutoModelForCausalLM": "modeling_cogvlm.CogVLMForCausalLM" | |
| }, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128009 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_multi_query_heads": 8, | |
| "pad_token_id": 128002, | |
| "quantization_config": { | |
| "amp": true, | |
| "autoround_version": "0.4.2.dev", | |
| "batch_size": 8, | |
| "bits": 4, | |
| "damp_percent": 0.01, | |
| "data_type": "int", | |
| "desc_act": false, | |
| "enable_minmax_tuning": true, | |
| "enable_norm_bias_tuning": false, | |
| "enable_quanted_input": true, | |
| "gradient_accumulate_steps": 1, | |
| "group_size": 128, | |
| "iters": 1, | |
| "low_gpu_mem_usage": false, | |
| "lr": 1.0, | |
| "minmax_lr": 1.0, | |
| "nsamples": 512, | |
| "quant_method": "gptq", | |
| "scale_dtype": "torch.float16", | |
| "seqlen": 512, | |
| "sym": true, | |
| "to_quant_block_names": [ | |
| [ | |
| "model.layers.0", | |
| "model.layers.1", | |
| "model.layers.2", | |
| "model.layers.3", | |
| "model.layers.4", | |
| "model.layers.5", | |
| "model.layers.6", | |
| "model.layers.7", | |
| "model.layers.8", | |
| "model.layers.9", | |
| "model.layers.10", | |
| "model.layers.11", | |
| "model.layers.12", | |
| "model.layers.13", | |
| "model.layers.14", | |
| "model.layers.15", | |
| "model.layers.16", | |
| "model.layers.17", | |
| "model.layers.18", | |
| "model.layers.19", | |
| "model.layers.20", | |
| "model.layers.21", | |
| "model.layers.22", | |
| "model.layers.23", | |
| "model.layers.24", | |
| "model.layers.25", | |
| "model.layers.26", | |
| "model.layers.27", | |
| "model.layers.28", | |
| "model.layers.29", | |
| "model.layers.30", | |
| "model.layers.31" | |
| ] | |
| ], | |
| "true_sequential": false | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "template_version": "chat", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "vision_config": { | |
| "dropout_prob": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1792, | |
| "image_size": 1344, | |
| "in_channels": 3, | |
| "intermediate_size": 15360, | |
| "layer_norm_eps": 1e-06, | |
| "num_heads": 16, | |
| "num_hidden_layers": 63, | |
| "num_positions": 9217, | |
| "patch_size": 14 | |
| }, | |
| "vocab_size": 128256 | |
| } | |