| { | |
| "_name_or_path": "models/allenai_Molmo-72B-0924", | |
| "architectures": [ | |
| "MolmoForCausalLM" | |
| ], | |
| "attention_layer_norm": false, | |
| "auto_map": { | |
| "AutoConfig": "config_molmo.MolmoConfig", | |
| "AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM" | |
| }, | |
| "clip_qkv": null, | |
| "embedding_size": 152064, | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 59136, | |
| "layer_norm_eps": 1e-05, | |
| "layer_norm_type": "rms", | |
| "max_position_embeddings": 4096, | |
| "model_type": "molmo", | |
| "norm_after": false, | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "qkv_bias": 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": "nf4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": true, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": ["model.wte", "model.ln_f", "model.transformer.ff_out", "model.vision_backbone"], | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.1", | |
| "use_cache": true, | |
| "use_position_ids": true, | |
| "vocab_size": 152064, | |
| "weight_tying": false | |
| } | |