| { | |
| "_name_or_path": "./tmp_autoround_awq", | |
| "architectures": [ | |
| "GraniteForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.1, | |
| "attention_multiplier": 0.0078125, | |
| "bos_token_id": 0, | |
| "embedding_multiplier": 12.0, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12800, | |
| "logits_scaling": 16.0, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "granite", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "backend": "autoawq", | |
| "bits": 4, | |
| "do_fuse": false, | |
| "exllama_config": null, | |
| "fuse_max_seq_len": null, | |
| "group_size": 128, | |
| "modules_to_fuse": null, | |
| "modules_to_not_convert": [ | |
| "lm_head" | |
| ], | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": false | |
| }, | |
| "residual_multiplier": 0.22, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.1", | |
| "use_cache": true, | |
| "vocab_size": 49155 | |
| } | |