linux-as-a-model-5M / config.json
mjbommar's picture
Upload TextGenerationPipeline
40aa84a verified
raw
history blame
730 Bytes
{
"_name_or_path": "/nas4/data/checkpoints/laam-v1.0-5M",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 64,
"initializer_range": 0.02,
"intermediate_size": 256,
"max_position_embeddings": 512,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 8,
"num_key_value_heads": 4,
"pad_token_id": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32769
}