jd3 / config.json
stojchet's picture
Training in progress, step 35
b6503e2 verified
raw
history blame
770 Bytes
{
"_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 32013,
"eos_token_id": 32014,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 100000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.43.0.dev0",
"use_cache": true,
"vocab_size": 32256
}