| { | |
| "_name_or_path": "allenai/OLMo-2-1124-7B", | |
| "architectures": [ | |
| "Olmo2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "eos_token_id": 100257, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "model_type": "olmo2", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 100277, | |
| "quantization_config": { | |
| "amp": false, | |
| "autoround_version": "0.4.2", | |
| "backend": "auto_round:gptq:exllamav2", | |
| "batch_size": 4, | |
| "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": 200, | |
| "low_gpu_mem_usage": false, | |
| "lr": 0.005, | |
| "minmax_lr": 0.005, | |
| "nsamples": 128, | |
| "quant_method": "intel/auto-round", | |
| "scale_dtype": "torch.float16", | |
| "seqlen": 512, | |
| "sym": true, | |
| "to_quant_block_names": null | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 500000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0", | |
| "use_cache": true, | |
| "vocab_size": 100352 | |
| } | |