| { |
| "architectures": [ |
| "SolarOpenForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_solar_open.SolarOpenConfig", |
| "AutoModel": "modeling_solar_open.SolarOpenModel", |
| "AutoModelForCausalLM": "modeling_solar_open.SolarOpenForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 2, |
| "first_k_dense_replace": 0, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "max_position_embeddings": 131072, |
| "model_type": "solar_open", |
| "moe_intermediate_size": 1280, |
| "n_group": 1, |
| "n_routed_experts": 128, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 8, |
| "pad_token_id": 2, |
| "partial_rotary_factor": 1.0, |
| "quantization_config": { |
| "bits": 4, |
| "data_type": "int", |
| "group_size": 128, |
| "packing_format": "auto_round:auto_gptq", |
| "quant_method": "auto-round", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "routed_scaling_factor": 1.0, |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "transformers_version": "4.57.3", |
| "use_cache": true, |
| "use_qk_norm": false, |
| "vocab_size": 196608 |
| } |
|
|