| { | |
| "_name_or_path": "Qwen/Qwen-7B", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig", | |
| "AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel" | |
| }, | |
| "bf16": false, | |
| "bos_token_id": null, | |
| "emb_dropout_prob": 0.0, | |
| "eos_token_id": null, | |
| "fp16": false, | |
| "fp32": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 22016, | |
| "kv_channels": 128, | |
| "layer_norm_epsilon": 1e-06, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mixtral", | |
| "no_bias": true, | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 2, | |
| "onnx_safe": null, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "scale_attn_weights": true, | |
| "seq_length": 8192, | |
| "sliding_window": null, | |
| "softmax_in_fp32": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "QWenTokenizer", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "use_cache_kernel": false, | |
| "use_cache_quantization": false, | |
| "use_dynamic_ntk": true, | |
| "use_flash_attn": "auto", | |
| "use_logn_attn": true, | |
| "vocab_size": 151936 | |
| } | |