{ | |
"_name_or_path": "sudhanshu746/Deepseek-math-7B-arithmetic-mk-v2", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"attention_bias": false, | |
"attention_dropout": 0.0, | |
"bos_token_id": 100000, | |
"eos_token_id": 100001, | |
"hidden_act": "silu", | |
"hidden_size": 4096, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 4096, | |
"mlp_bias": false, | |
"model_type": "llama", | |
"num_attention_heads": 32, | |
"num_hidden_layers": 30, | |
"num_key_value_heads": 32, | |
"pretraining_tp": 1, | |
"quantization_config": { | |
"bits": 4, | |
"checkpoint_format": "gptq", | |
"damp_percent": 0.01, | |
"desc_act": false, | |
"group_size": 128, | |
"model_file_base_name": null, | |
"model_name_or_path": null, | |
"quant_method": "gptq", | |
"static_groups": false, | |
"sym": true, | |
"true_sequential": true | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_scaling": null, | |
"rope_theta": 10000.0, | |
"tie_word_embeddings": false, | |
"torch_dtype": "float16", | |
"transformers_version": "4.41.2", | |
"use_cache": true, | |
"vocab_size": 102400 | |
} | |