CoolFace
Modelpublic

onnx-internal-testing/tiny-random-SolarOpenForCausalLM

sourceHugging Faceupdated 6mo agoView on Hugging Face
0likes745downloads
config.json54 linesDownload Raw Back to root
1{2  "architectures": [3    "SolarOpenForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "dtype": "float32",9  "eos_token_id": 2,10  "first_k_dense_replace": 0,11  "head_dim": 16,12  "hidden_act": "silu",13  "hidden_size": 64,14  "initializer_range": 0.02,15  "intermediate_size": 10240,16  "max_position_embeddings": 131072,17  "model_type": "solar_open",18  "moe_intermediate_size": 16,19  "n_group": 1,20  "n_routed_experts": 4,21  "n_shared_experts": 1,22  "norm_topk_prob": true,23  "num_attention_heads": 4,24  "num_experts_per_tok": 2,25  "num_hidden_layers": 2,26  "num_key_value_heads": 2,27  "pad_token_id": 2,28  "partial_rotary_factor": 1.0,29  "rms_norm_eps": 1e-05,30  "rope_parameters": {31    "factor": 2.0,32    "original_max_position_embeddings": 65536,33    "partial_rotary_factor": 1.0,34    "rope_theta": 1000000,35    "rope_type": "yarn",36    "type": "yarn"37  },38  "routed_scaling_factor": 1.0,39  "tie_word_embeddings": false,40  "topk_group": 1,41  "transformers_version": "5.3.0.dev0",42  "use_cache": true,43  "vocab_size": 196608,44  "transformers.js_config": {45    "use_external_data_format": {46      "model.onnx": 1,47      "model_fp16.onnx": 148    },49    "kv_cache_dtype": {50      "q4f16": "float16",51      "fp16": "float16"52    }53  }54}