| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "NousResearch/Yarn-Mistral-7b-128k", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "NousResearch/Yarn-Mistral-7b-128k--configuration_mistral.MistralConfig", | |
| "AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-128k--modeling_mistral_yarn.MistralForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "max_sequence_length": 131072, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 16.0, | |
| "finetuned": true, | |
| "original_max_position_embeddings": 8192, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.0", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |