| { | |
| "_name_or_path": "/models/OLMo-2-1124-13B-Instruct", | |
| "architectures": [ | |
| "Olmo2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "eos_token_id": 100257, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 4096, | |
| "model_type": "olmo2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pad_token_id": 100277, | |
| "quantization_config": { | |
| "amp": true, | |
| "autoround_version": "0.4.2.dev", | |
| "backend": "auto_round:gptq:exllamav2", | |
| "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": "intel/auto-round", | |
| "scale_dtype": "torch.float16", | |
| "seqlen": 2048, | |
| "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", | |
| "model.layers.32", | |
| "model.layers.33", | |
| "model.layers.34", | |
| "model.layers.35", | |
| "model.layers.36", | |
| "model.layers.37", | |
| "model.layers.38", | |
| "model.layers.39" | |
| ] | |
| ] | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 500000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.47.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 100352 | |
| } | |