| { | |
| "_name_or_path": "./", | |
| "architectures": [ | |
| "InfiMMZephyrModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_infimm_zephyr.InfiMMConfig", | |
| "AutoModelForCausalLM": "modeling_infimm_zephyr.InfiMMZephyrModel" | |
| }, | |
| "model_type": "infimm-zephyr", | |
| "seq_length": 1024, | |
| "tokenizer_type": "LlamaTokenizer", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "use_flash_attn": false, | |
| "cross_attn_every_n_layers": 2, | |
| "use_grad_checkpoint": false, | |
| "freeze_llm": true, | |
| "image_token_id": 32001, | |
| "eoc_token_id": 32000, | |
| "visual": { | |
| "image_size": 336, | |
| "layers": 24, | |
| "width": 1024, | |
| "head_width": 64, | |
| "patch_size": 14, | |
| "mlp_ratio": 2.6667, | |
| "eva_model_name": "eva-clip-l-14-336", | |
| "drop_path_rate": 0.0, | |
| "xattn": false, | |
| "fusedLN": true, | |
| "rope": true, | |
| "pt_hw_seq_len": 16, | |
| "intp_freq": true, | |
| "naiveswiglu": true, | |
| "subln": true, | |
| "embed_dim": 768 | |
| }, | |
| "language": { | |
| "_name_or_path": "HuggingFaceH4/zephyr-7b-beta", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.35.0", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| } |