| { | |
| "_name_or_path": "/workspace/multihumpbackplus/pretraining/cat_wiki_kuj_aug_oas_shar_unleashed_qwen", | |
| "architectures": [ | |
| "QWenLMHeadModel" | |
| ], | |
| "attn_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_qwen.QWenConfig", | |
| "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel" | |
| }, | |
| "bf16": true, | |
| "emb_dropout_prob": 0.0, | |
| "fp16": false, | |
| "fp32": false, | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27392, | |
| "kv_channels": 128, | |
| "layer_norm_epsilon": 1e-06, | |
| "max_position_embeddings": 8192, | |
| "model_type": "qwen", | |
| "no_bias": true, | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "onnx_safe": null, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "scale_attn_weights": true, | |
| "seq_length": 8192, | |
| "softmax_in_fp32": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "QWenTokenizer", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.0.dev0", | |
| "use_cache": false, | |
| "use_cache_kernel": false, | |
| "use_cache_quantization": false, | |
| "use_dynamic_ntk": true, | |
| "use_flash_attn": true, | |
| "use_logn_attn": true, | |
| "vocab_size": 152064 | |
| } | |