| { |
| "_name_or_path": "10302244_iter8000_final/", |
| "architectures": [ |
| "QWenLMHeadModel" |
| ], |
| "attn_dropout_prob": 0.0, |
| "audio": { |
| "add_audio_bos_eos_token": true, |
| "audio_start_id": 155164, |
| "avg_pool": true, |
| "n_ctx": 1500, |
| "n_head": 20, |
| "n_layer": 32, |
| "n_mels": 80, |
| "n_state": 1280, |
| "output_dim": 4096 |
| }, |
| "auto_map": { |
| "AutoConfig": "configuration_qwen.QWenConfig", |
| "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel" |
| }, |
| "bf16": false, |
| "emb_dropout_prob": 0.0, |
| "fp16": true, |
| "fp32": false, |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 22016, |
| "kv_channels": 128, |
| "layer_norm_epsilon": 1e-05, |
| "max_position_embeddings": 8192, |
| "model_type": "qwen", |
| "no_bias": true, |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "onnx_safe": null, |
| "rotary_emb_base": 10000, |
| "rotary_pct": 1.0, |
| "scale_attn_weights": true, |
| "seq_length": 2048, |
| "softmax_in_fp32": false, |
| "tie_word_embeddings": false, |
| "tokenizer_type": "QWenTokenizer", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.32.0", |
| "use_cache": true, |
| "use_cache_kernel": false, |
| "use_cache_quantization": false, |
| "use_dynamic_ntk": true, |
| "use_flash_attn": true, |
| "use_logn_attn": true, |
| "vocab_size": 155947 |
| } |
|
|
