3b5e2884a6
Model: zhenting/evolm-1B-160BT-cpt-MixedFW8FM42-sftep1-sampled500k_first100k_qwen7b Source: Original Platform
31 lines
741 B
JSON
31 lines
741 B
JSON
{
|
|
"_name_or_path": "zhenting/myllama-1B-160BT-cpt-MixedFW8FM42",
|
|
"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": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 4896,
|
|
"max_position_embeddings": 2048,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 22,
|
|
"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": "bfloat16",
|
|
"transformers_version": "4.46.1",
|
|
"use_cache": false,
|
|
"vocab_size": 32000
|
|
}
|