{ | |
"_name_or_path": "/content/RuQwen2.5-3B-Instruct-AWQ", | |
"add_bias_to_lm_head": true, | |
"architectures": [ | |
"RuQwen2ForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"bos_token_id": 121125, | |
"eos_token_id": 121127, | |
"hidden_act": "silu", | |
"hidden_size": 2048, | |
"initializer_range": 0.02, | |
"intermediate_size": 11008, | |
"max_position_embeddings": 32768, | |
"max_window_layers": 70, | |
"model_type": "qwen2", | |
"num_attention_heads": 16, | |
"num_hidden_layers": 36, | |
"num_key_value_heads": 2, | |
"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": null, | |
"quant_method": "awq", | |
"version": "gemm", | |
"zero_point": true | |
}, | |
"rms_norm_eps": 1e-06, | |
"rope_theta": 1000000.0, | |
"sliding_window": null, | |
"tie_word_embeddings": true, | |
"torch_dtype": "float16", | |
"transformers_version": "4.44.2", | |
"use_cache": true, | |
"use_sliding_window": false, | |
"vocab_size": 121147 | |
} | |