hf-transformers-bot's picture
Update tiny models for SolarOpenForCausalLM
fd8da64 verified
Raw
History Blame Contribute Delete
951 Bytes
{
"architectures": [
"SolarOpenForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 16,
"hidden_act": "gelu",
"hidden_size": 32,
"initializer_range": 0.02,
"is_decoder": true,
"max_position_embeddings": 512,
"model_type": "solar_open",
"moe_intermediate_size": 16,
"n_group": 1,
"n_routed_experts": 8,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 2,
"num_experts_per_tok": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"pad_token_id": 2,
"partial_rotary_factor": 1.0,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"partial_rotary_factor": 1.0,
"rope_theta": 1000000.0,
"rope_type": "default"
},
"routed_scaling_factor": 1.0,
"tie_word_embeddings": false,
"topk_group": 1,
"transformers_version": "5.16.0.dev0",
"use_cache": true,
"vocab_size": 196608
}