| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "/fsx/ubuntu/.cache/huggingface/hub/models--cyberagent--Mistral-Nemo-Japanese-Instruct-2408/snapshots/8591f78522a5d651209fc9f354c848508db7a3eb", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 131072, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 1024000, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 10, | |
| "quantization_config": { | |
| "bits": 4, | |
| "checkpoint_format": "gptq", | |
| "desc_act": false, | |
| "dynamic": null, | |
| "group_size": 32, | |
| "lm_head": false, | |
| "meta": { | |
| "damp_auto_increment": 0.0025, | |
| "damp_percent": 0.01, | |
| "mse": 0.0, | |
| "quantizer": [ | |
| "gptqmodel:1.7.0" | |
| ], | |
| "static_groups": false, | |
| "true_sequential": true, | |
| "uri": "https://github.com/modelcloud/gptqmodel" | |
| }, | |
| "quant_method": "gptq", | |
| "sym": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.0", | |
| "use_cache": false, | |
| "vocab_size": 131074 | |
| } | |