genne's picture
Training in progress, step 500
ba3a710 verified
raw
history blame contribute delete
701 Bytes
{
"_name_or_path": "HuggingFaceTB/SmolLM-135M",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 576,
"initializer_range": 0.02,
"intermediate_size": 1536,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 9,
"num_hidden_layers": 30,
"num_key_value_heads": 3,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.43.2",
"use_cache": true,
"vocab_size": 49152
}