| { | |
| "model_type": "solar_open", | |
| "architectures": [ | |
| "SolarOpenForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_solar_open.SolarOpenConfig", | |
| "AutoModel": "modeling_solar_open.SolarOpenModel", | |
| "AutoModelForCausalLM": "modeling_solar_open.SolarOpenForCausalLM" | |
| }, | |
| "pad_token_id": 2, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "partial_rotary_factor": 1.0, | |
| "hidden_size": 4096, | |
| "num_hidden_layers": 48, | |
| "num_attention_heads": 64, | |
| "head_dim": 128, | |
| "num_key_value_heads": 8, | |
| "vocab_size": 196608, | |
| "intermediate_size": 10240, | |
| "moe_intermediate_size": 1280, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000, | |
| "max_position_embeddings": 131072, | |
| "n_routed_experts": 128, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "routed_scaling_factor": 1.0, | |
| "num_experts_per_tok": 8, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "first_k_dense_replace": 0, | |
| "use_cache": true, | |
| "transformers_version": "4.57.1", | |
| "rope_scaling": { | |
| "type": "yarn", | |
| "factor": 2.0, | |
| "original_max_position_embeddings": 65536 | |
| } | |
| } |