| { | |
| "_name_or_path": "HuggingFaceTB/SmolLM2-1.7B", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "amp": false, | |
| "autoround_version": "0.4.2", | |
| "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, | |
| "modules_to_not_convert": [ | |
| "lm_head" | |
| ], | |
| "nsamples": 128, | |
| "quant_method": "awq", | |
| "scale_dtype": "torch.float16", | |
| "seqlen": 512, | |
| "sym": false, | |
| "to_quant_block_names": null, | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 130000, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0", | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } | |