xDAN-L1-SOLAR-RL-v1 / config.json
xDAN2099's picture
Upload folder using huggingface_hub
51f9104
raw
history blame contribute delete
713 Bytes
{
"_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 32000
}