Mermaid-Llama-6.7B-RAG / config.json
TroyDoesAI's picture
1 Epoch of Contextual Accuracy, 1 Epoch of Python Instruct, 1 Epoch of Python to Mermaid Graphs
b1e5bc7 verified
raw
history blame contribute delete
No virus
753 Bytes
{
"_name_or_path": ".\\Mermaid\\",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 32013,
"eos_token_id": 32014,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 100000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.39.3",
"use_cache": false,
"vocab_size": 32023
}