Text Generation
Transformers
PyTorch
Safetensors
German
llama
text-generation-inference
LLaMmlein_120M / config.json
Julia287's picture
Adding final model
6be26af verified
raw
history blame contribute delete
776 Bytes
{
"_name_or_path": "/hnvme/workspace/b185cb13-llammlein/anvme/models/120M_fa3_new/iter-01430512-ckpt",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.47.0",
"use_cache": true,
"vocab_size": 32064
}