|
{ |
|
"_name_or_path": "/data/haolu/ckpt/Qwen1.5-32B-Chat", |
|
"architectures": [ |
|
"Qwen2ForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 151643, |
|
"eos_token_id": 151645, |
|
"hidden_act": "silu", |
|
"hidden_size": 5120, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 27392, |
|
"max_position_embeddings": 32768, |
|
"max_window_layers": 35, |
|
"model_type": "qwen2", |
|
"num_attention_heads": 40, |
|
"num_hidden_layers": 64, |
|
"num_key_value_heads": 8, |
|
"quantization_config": { |
|
"codebook": "E8P12RVQ3B", |
|
"codesz": 8, |
|
"idx_dtype": "torch.int32", |
|
"merge_suv": false, |
|
"modules_to_not_convert": null, |
|
"opt_resid_scale": -1, |
|
"per_channel": false, |
|
"quant_method": "QUiP", |
|
"rescale_WH": false, |
|
"use_rand": true |
|
}, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": 32768, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.40.2", |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 152064 |
|
} |
|
|