| { | |
| "_name_or_path": "/workspace/process/acrastt_marx-3b-v3/source", | |
| "architectures": [ | |
| "StableLMEpochForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig", | |
| "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "max_position_embeddings": 4096, | |
| "model_type": "stablelm_epoch", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "model.layers", | |
| "damp_percent": 0.1, | |
| "desc_act": true, | |
| "disable_exllama": false, | |
| "group_size": 128, | |
| "max_input_length": null, | |
| "model_seqlen": 4096, | |
| "module_name_preceding_first_block": [ | |
| "model.embed_tokens" | |
| ], | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": true, | |
| "use_cuda_fp16": true | |
| }, | |
| "rope_pct": 0.25, | |
| "rope_theta": 10000, | |
| "rotary_scaling_factor": 1.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 50304 | |
| } |