| { |
| "_name_or_path": "/data6/models/Molmo-7B-D-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": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 37888, |
| "layer_norm_eps": 1e-06, |
| "layer_norm_type": "rms", |
| "max_position_embeddings": 4096, |
| "model_type": "molmo", |
| "norm_after": false, |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "qkv_bias": true, |
| "quantization_config": { |
| "amp": true, |
| "autoround_version": "0.4.4", |
| "batch_size": 8, |
| "bits": 4, |
| "data_type": "int", |
| "dataset": "NeelNanda/pile-10k", |
| "enable_minmax_tuning": true, |
| "enable_norm_bias_tuning": false, |
| "enable_quanted_input": true, |
| "gradient_accumulate_steps": 1, |
| "group_size": 128, |
| "iters": 1000, |
| "low_gpu_mem_usage": false, |
| "lr": 0.001, |
| "minmax_lr": 0.001, |
| "nsamples": 512, |
| "quant_method": "auto-round", |
| "scale_dtype": "torch.float16", |
| "seqlen": 2048, |
| "sym": true, |
| "block_name_to_quantize": "model.transformer.blocks" |
| }, |
| "rope_theta": 1000000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.47.1", |
| "use_cache": true, |
| "use_position_ids": true, |
| "vocab_size": 152064, |
| "weight_tying": false |
| } |
|
|
