{ "version": "0.1.0", "model_type": "llava", "quantization": "q0f16", "model_config": { "image_token_index": 32000, "text_config": { "hidden_size": 4096, "intermediate_size": 11008, "num_attention_heads": 32, "num_hidden_layers": 32, "rms_norm_eps": 1e-05, "vocab_size": 32000, "position_embedding_base": 10000.0, "context_window_size": 4096, "prefill_chunk_size": 2048, "num_key_value_heads": 32, "head_dim": 128, "tensor_parallel_shards": 1, "max_batch_size": 1, "kwargs": { "_name_or_path": "lmsys/vicuna-7b-v1.5", "architectures": [ "LlamaForCausalLM" ], "model_type": "llama", "torch_dtype": "float16", "hidden_act": "silu", "initializer_range": 0.02, "pretraining_tp": 1, "use_cache": true, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "transformers_version": "4.41.2" } }, "vision_config": { "hidden_size": 1024, "image_size": 336, "intermediate_size": 4096, "num_attention_heads": 16, "num_hidden_layers": 24, "patch_size": 14, "projection_dim": 768, "vocab_size": 32000, "num_channels": 3, "layer_norm_eps": 1e-06, "kwargs": { "model_type": "clip_vision_model" } }, "vocab_size": 32064, "context_window_size": 4096, "sliding_window_size": -1, "prefill_chunk_size": 2048, "tensor_parallel_shards": 1, "max_batch_size": 80, "text_architecture": "LlamaForCausalLM" }, "vocab_size": 32064, "context_window_size": 4096, "sliding_window_size": -1, "prefill_chunk_size": 2048, "attention_sink_size": -1, "tensor_parallel_shards": 1, "temperature": 1.0, "presence_penalty": 0.0, "frequency_penalty": 0.0, "repetition_penalty": 1.0, "top_p": 1.0, "tokenizer_files": [ "tokenizer.model", "tokenizer.json", "added_tokens.json", "tokenizer_config.json" ], "tokenizer_info": { "token_postproc_method": "byte_fallback", "prepend_space_in_encode": true, "strip_space_in_decode": true }, "conv_template": { "name": "llava", "system_template": "{system_message}", "system_message": "\n", "system_prefix_token_ids": [ 1 ], "add_role_after_system_message": false, "roles": { "user": "USER", "assistant": "ASSISTANT" }, "role_templates": { "user": "{user_message}", "assistant": "{assistant_message}", "tool": "{tool_message}" }, "messages": [], "seps": [ " " ], "role_content_sep": ": ", "role_empty_sep": ":", "stop_str": [ "" ], "stop_token_ids": [ 2 ], "function_string": "", "use_function_calling": false }, "pad_token_id": 32001, "bos_token_id": 1, "eos_token_id": 2 }